Faro Qwen 4b model

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/cephfs/panwenbo/work/repos/fusang_8x7b/outputs/fi-chatml-4/merged",
+  "architectures": [
+    "Qwen2Model"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 20,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "type": "dynamic"
+  },
+  "rope_theta": 5000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:294f7c3ed464762c4810158552f9db17f93e383683dd64fd788740e50e0e43ad
+size 4989971528

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e257877f7a4c582344782b3e1d9dda0d9f3b116edb2b97fa103ffddb82e49480
+size 2132907008

model.safetensors.index.json

@@ -0,0 +1,489 @@
+{
+  "metadata": {
+    "total_size": 7122826240
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.36.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.36.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.36.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.36.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.36.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.36.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.37.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.37.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.37.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.37.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.37.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.38.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.38.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.38.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.38.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.39.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.39.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.39.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.39.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.39.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "norm.weight": "model-00002-of-00002.safetensors"
+  }
+}