diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json"
--- "a/model.safetensors.index.json"
+++ "b/model.safetensors.index.json"
@@ -1,1268 +1,1596 @@
 {
     "metadata": {
-        "total_size": 5516385504
+        "total_size": 4747823648
     },
     "weight_map": {
-        "connector.modality_projection.down_proj.biases": "model-00001-of-00002.safetensors",
-        "connector.modality_projection.down_proj.scales": "model-00001-of-00002.safetensors",
-        "connector.modality_projection.down_proj.weight": "model-00001-of-00002.safetensors",
-        "connector.modality_projection.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "connector.modality_projection.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "connector.modality_projection.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "connector.modality_projection.up_proj.biases": "model-00001-of-00002.safetensors",
-        "connector.modality_projection.up_proj.scales": "model-00001-of-00002.safetensors",
-        "connector.modality_projection.up_proj.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.latents": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.input_context_norm.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.input_latents_norm.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.input_context_norm.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.input_latents_norm.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.input_context_norm.weight": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.input_latents_norm.weight": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-        "connector.perceiver_resampler.norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.lm_head.biases": "model-00001-of-00002.safetensors",
-        "language_model.lm_head.scales": "model-00001-of-00002.safetensors",
-        "language_model.lm_head.weight": "model-00001-of-00002.safetensors",
-        "language_model.norm.weight": "model-00001-of-00002.safetensors",
-        "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
-        "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
-        "vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-        "vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
-        "vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
+        "connector.modality_projection.down_proj.biases": "model.safetensors",
+        "connector.modality_projection.down_proj.scales": "model.safetensors",
+        "connector.modality_projection.down_proj.weight": "model.safetensors",
+        "connector.modality_projection.gate_proj.biases": "model.safetensors",
+        "connector.modality_projection.gate_proj.scales": "model.safetensors",
+        "connector.modality_projection.gate_proj.weight": "model.safetensors",
+        "connector.modality_projection.up_proj.biases": "model.safetensors",
+        "connector.modality_projection.up_proj.scales": "model.safetensors",
+        "connector.modality_projection.up_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.latents": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.input_context_norm.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.input_latents_norm.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.mlp.down_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.mlp.down_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.mlp.gate_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.mlp.gate_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.mlp.up_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.mlp.up_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.self_attn.k_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.self_attn.k_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.self_attn.o_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.self_attn.o_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.self_attn.q_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.self_attn.q_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.self_attn.v_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.self_attn.v_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.input_context_norm.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.input_latents_norm.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.mlp.down_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.mlp.down_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.mlp.gate_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.mlp.gate_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.mlp.up_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.mlp.up_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.self_attn.k_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.self_attn.k_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.self_attn.o_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.self_attn.o_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.self_attn.q_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.self_attn.q_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.self_attn.v_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.self_attn.v_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.input_context_norm.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.input_latents_norm.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.mlp.down_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.mlp.down_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.mlp.gate_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.mlp.gate_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.mlp.up_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.mlp.up_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.self_attn.k_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.self_attn.k_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.self_attn.o_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.self_attn.o_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.self_attn.q_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.self_attn.q_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.self_attn.v_proj.biases": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.self_attn.v_proj.scales": "model.safetensors",
+        "connector.perceiver_resampler.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "connector.perceiver_resampler.norm.weight": "model.safetensors",
+        "language_model.embed_tokens.biases": "model.safetensors",
+        "language_model.embed_tokens.scales": "model.safetensors",
+        "language_model.embed_tokens.weight": "model.safetensors",
+        "language_model.layers.0.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.0.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.0.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.0.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.0.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.0.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.0.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.0.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.0.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.0.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.0.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.0.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.0.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.0.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.0.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.1.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.1.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.1.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.1.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.1.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.1.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.1.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.1.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.1.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.1.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.1.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.1.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.1.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.1.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.1.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.10.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.10.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.10.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.10.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.10.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.10.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.10.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.10.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.10.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.10.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.10.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.10.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.10.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.10.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.10.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.11.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.11.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.11.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.11.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.11.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.11.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.11.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.11.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.11.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.11.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.11.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.11.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.11.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.11.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.11.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.12.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.12.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.12.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.12.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.12.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.12.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.12.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.12.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.12.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.12.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.12.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.12.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.12.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.12.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.12.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.12.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.13.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.13.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.13.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.13.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.13.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.13.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.13.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.13.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.13.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.13.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.13.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.13.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.13.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.13.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.13.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.13.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.14.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.14.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.14.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.14.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.14.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.14.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.14.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.14.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.14.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.14.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.14.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.14.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.14.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.14.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.14.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.14.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.15.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.15.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.15.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.15.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.15.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.15.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.15.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.15.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.15.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.15.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.15.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.15.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.15.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.15.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.15.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.15.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.16.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.16.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.16.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.16.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.16.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.16.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.16.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.16.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.16.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.16.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.16.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.16.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.16.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.16.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.16.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.16.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.16.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.17.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.17.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.17.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.17.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.17.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.17.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.17.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.17.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.17.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.17.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.17.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.17.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.17.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.17.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.17.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.17.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.17.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.17.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.17.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.17.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.18.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.18.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.18.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.18.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.18.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.18.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.18.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.18.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.18.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.18.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.18.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.18.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.18.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.18.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.18.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.18.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.18.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.18.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.18.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.18.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.18.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.18.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.19.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.19.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.19.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.19.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.19.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.19.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.19.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.19.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.19.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.19.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.19.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.19.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.19.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.19.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.19.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.19.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.19.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.19.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.19.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.19.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.19.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.2.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.2.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.2.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.2.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.2.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.2.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.2.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.2.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.2.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.2.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.2.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.2.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.2.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.2.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.2.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.20.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.20.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.20.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.20.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.20.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.20.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.20.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.20.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.20.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.20.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.20.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.20.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.20.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.20.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.20.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.20.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.20.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.20.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.20.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.20.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.20.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.20.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.21.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.21.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.21.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.21.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.21.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.21.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.21.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.21.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.21.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.21.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.21.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.21.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.21.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.21.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.21.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.21.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.21.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.21.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.21.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.21.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.21.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.21.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.22.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.22.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.22.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.22.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.22.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.22.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.22.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.22.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.22.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.22.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.22.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.22.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.22.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.22.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.22.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.22.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.22.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.22.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.22.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.22.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.22.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.22.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.23.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.23.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.23.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.23.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.23.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.23.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.23.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.23.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.23.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.23.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.23.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.23.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.23.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.23.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.23.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.23.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.23.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.23.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.23.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.23.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.23.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.23.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.24.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.24.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.24.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.24.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.24.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.24.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.24.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.24.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.24.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.24.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.24.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.24.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.24.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.24.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.24.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.24.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.24.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.24.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.24.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.24.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.24.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.24.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.24.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.25.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.25.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.25.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.25.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.25.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.25.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.25.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.25.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.25.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.25.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.25.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.25.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.25.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.25.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.25.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.25.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.25.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.25.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.25.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.25.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.25.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.25.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.25.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.26.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.26.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.26.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.26.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.26.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.26.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.26.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.26.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.26.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.26.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.26.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.26.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.26.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.26.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.26.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.26.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.26.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.26.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.26.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.26.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.26.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.26.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.26.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.27.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.27.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.27.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.27.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.27.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.27.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.27.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.27.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.27.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.27.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.27.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.27.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.27.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.27.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.27.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.27.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.27.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.27.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.27.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.27.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.27.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.27.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.27.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.28.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.28.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.28.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.28.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.28.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.28.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.28.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.28.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.28.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.28.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.28.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.28.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.28.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.28.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.28.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.28.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.28.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.28.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.28.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.28.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.28.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.28.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.28.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.29.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.29.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.29.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.29.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.29.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.29.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.29.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.29.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.29.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.29.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.29.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.29.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.29.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.29.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.29.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.29.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.29.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.29.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.29.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.29.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.29.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.29.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.29.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.3.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.3.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.3.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.3.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.3.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.3.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.3.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.3.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.3.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.3.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.3.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.3.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.3.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.3.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.3.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.30.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.30.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.30.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.30.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.30.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.30.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.30.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.30.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.30.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.30.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.30.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.30.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.30.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.30.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.30.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.30.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.30.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.30.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.30.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.30.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.30.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.30.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.30.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.31.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.31.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.31.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.31.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.31.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.31.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.31.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.31.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.31.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.31.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.31.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.31.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.31.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.31.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.31.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.31.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.31.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.31.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.31.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.31.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.31.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.31.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.31.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.4.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.4.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.4.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.4.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.4.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.4.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.4.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.4.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.4.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.4.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.4.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.4.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.4.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.4.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.4.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.5.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.5.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.5.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.5.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.5.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.5.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.5.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.5.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.5.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.5.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.5.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.5.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.5.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.5.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.5.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.6.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.6.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.6.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.6.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.6.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.6.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.6.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.6.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.6.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.6.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.6.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.6.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.6.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.6.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.6.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.7.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.7.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.7.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.7.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.7.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.7.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.7.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.7.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.7.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.7.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.7.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.7.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.7.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.7.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.7.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.8.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.8.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.8.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.8.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.8.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.8.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.8.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.8.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.8.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.8.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.8.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.8.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.8.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.8.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.8.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.9.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.9.mlp.down_proj.biases": "model.safetensors",
+        "language_model.layers.9.mlp.down_proj.scales": "model.safetensors",
+        "language_model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.9.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.layers.9.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.9.mlp.up_proj.biases": "model.safetensors",
+        "language_model.layers.9.mlp.up_proj.scales": "model.safetensors",
+        "language_model.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.9.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.layers.9.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.9.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.layers.9.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.9.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.layers.9.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.9.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.layers.9.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.lm_head.biases": "model.safetensors",
+        "language_model.lm_head.scales": "model.safetensors",
+        "language_model.lm_head.weight": "model.safetensors",
+        "language_model.norm.weight": "model.safetensors",
+        "vision_model.embeddings.patch_embedding.bias": "model.safetensors",
+        "vision_model.embeddings.patch_embedding.weight": "model.safetensors",
+        "vision_model.embeddings.position_embedding.biases": "model.safetensors",
+        "vision_model.embeddings.position_embedding.scales": "model.safetensors",
+        "vision_model.embeddings.position_embedding.weight": "model.safetensors",
+        "vision_model.encoder.layers.0.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.0.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.0.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.0.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.0.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.0.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.0.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.0.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.0.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.0.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.0.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.0.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.1.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.1.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.1.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.1.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.1.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.1.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.1.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.1.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.1.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.1.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.1.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.1.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.10.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.10.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.10.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.10.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.10.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.10.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.10.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.10.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.10.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.10.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.10.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.10.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.11.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.11.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.11.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.11.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.11.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.11.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.11.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.11.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.11.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.11.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.11.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.11.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.12.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.12.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.12.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.12.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.12.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.12.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.12.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.12.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.12.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.12.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.12.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.12.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.12.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.12.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.12.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.12.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.12.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.12.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.12.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.12.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.12.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.12.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.12.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.12.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.12.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.13.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.13.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.13.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.13.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.13.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.13.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.13.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.13.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.13.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.13.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.13.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.13.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.13.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.13.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.13.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.13.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.13.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.13.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.13.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.13.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.13.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.13.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.13.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.13.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.13.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.14.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.14.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.14.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.14.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.14.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.14.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.14.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.14.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.14.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.14.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.14.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.14.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.14.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.14.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.14.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.14.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.14.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.14.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.14.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.14.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.14.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.14.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.14.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.14.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.14.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.15.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.15.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.15.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.15.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.15.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.15.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.15.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.15.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.15.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.15.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.15.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.15.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.15.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.15.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.15.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.15.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.15.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.15.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.15.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.15.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.15.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.15.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.15.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.15.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.15.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.16.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.16.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.16.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.16.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.16.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.16.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.16.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.16.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.16.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.16.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.16.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.16.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.16.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.16.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.16.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.16.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.16.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.16.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.16.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.16.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.16.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.16.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.16.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.16.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.16.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.16.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.16.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.17.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.17.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.17.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.17.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.17.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.17.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.17.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.17.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.17.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.17.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.17.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.17.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.17.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.17.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.17.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.17.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.17.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.17.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.17.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.17.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.17.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.17.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.17.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.17.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.17.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.17.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.17.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.17.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.18.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.18.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.18.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.18.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.18.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.18.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.18.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.18.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.18.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.18.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.18.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.18.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.18.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.18.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.18.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.18.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.18.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.18.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.18.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.18.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.18.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.18.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.18.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.18.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.18.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.18.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.18.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.18.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.19.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.19.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.19.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.19.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.19.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.19.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.19.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.19.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.19.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.19.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.19.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.19.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.19.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.19.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.19.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.19.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.19.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.19.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.19.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.19.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.19.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.19.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.19.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.19.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.19.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.19.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.19.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.19.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.2.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.2.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.2.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.2.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.2.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.2.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.2.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.2.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.2.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.2.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.2.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.2.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.20.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.20.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.20.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.20.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.20.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.20.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.20.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.20.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.20.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.20.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.20.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.20.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.20.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.20.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.20.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.20.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.20.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.20.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.20.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.20.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.20.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.20.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.20.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.20.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.20.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.20.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.20.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.20.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.21.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.21.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.21.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.21.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.21.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.21.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.21.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.21.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.21.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.21.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.21.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.21.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.21.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.21.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.21.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.21.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.21.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.21.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.21.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.21.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.21.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.21.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.21.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.21.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.21.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.21.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.21.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.21.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.22.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.22.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.22.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.22.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.22.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.22.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.22.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.22.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.22.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.22.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.22.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.22.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.22.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.22.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.22.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.22.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.22.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.22.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.22.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.22.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.22.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.22.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.22.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.22.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.22.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.22.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.22.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.22.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.23.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.23.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.23.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.23.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.23.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.23.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.23.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.23.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.23.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.23.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.23.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.23.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.23.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.23.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.23.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.23.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.23.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.23.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.23.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.23.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.23.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.23.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.23.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.23.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.23.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.23.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.23.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.23.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.24.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.24.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.24.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.24.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.24.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.24.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.24.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.24.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.24.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.24.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.24.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.24.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.24.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.24.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.24.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.24.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.24.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.24.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.24.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.24.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.24.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.24.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.24.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.24.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.24.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.24.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.24.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.24.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.25.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.25.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.25.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.25.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.25.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.25.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.25.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.25.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.25.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.25.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.25.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.25.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.25.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.25.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.25.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.25.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.25.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.25.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.25.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.25.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.25.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.25.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.25.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.25.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.25.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.25.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.25.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.25.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.26.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.26.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.26.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.26.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.26.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.26.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.26.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.26.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.26.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.26.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.26.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.26.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.26.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.26.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.26.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.26.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.26.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.26.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.26.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.26.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.26.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.26.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.26.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.26.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.26.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.26.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.26.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.26.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.3.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.3.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.3.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.3.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.3.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.3.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.3.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.3.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.3.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.3.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.3.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.3.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.4.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.4.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.4.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.4.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.4.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.4.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.4.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.4.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.4.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.4.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.4.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.4.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.5.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.5.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.5.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.5.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.5.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.5.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.5.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.5.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.5.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.5.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.5.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.5.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.6.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.6.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.6.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.6.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.6.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.6.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.6.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.6.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.6.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.6.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.6.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.6.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.7.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.7.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.7.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.7.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.7.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.7.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.7.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.7.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.7.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.7.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.7.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.7.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.8.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.8.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.8.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.8.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.8.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.8.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.8.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.8.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.8.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.8.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.8.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.8.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.9.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.9.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.9.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.9.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.9.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.9.mlp.fc1.biases": "model.safetensors",
+        "vision_model.encoder.layers.9.mlp.fc1.scales": "model.safetensors",
+        "vision_model.encoder.layers.9.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.9.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.9.mlp.fc2.biases": "model.safetensors",
+        "vision_model.encoder.layers.9.mlp.fc2.scales": "model.safetensors",
+        "vision_model.encoder.layers.9.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.k_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.k_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.out_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.out_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.q_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.q_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.v_proj.biases": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.v_proj.scales": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.post_layernorm.bias": "model.safetensors",
+        "vision_model.post_layernorm.weight": "model.safetensors"
     }
 }
\ No newline at end of file