Upload GemmaForCausalLM

README.md

@@ -1,6 +1,8 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- trl
+- sft
 ---
 
 # Model Card for Model ID

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "google/gemma-2b-it",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": null,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c0b2bc21e95ff486f3966a83c5dad16f0eb8f619a38f1b0e94112744c643538
+size 4974250976

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:074a37a32f611f616db09c7e90c402832cc4affd0f79ec6f312219baedacf722
+size 67564232

model.safetensors.index.json

@@ -0,0 +1,423 @@
+{
+  "metadata": {
+    "total_size": 5041762304
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}