Upload 6 files

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "liminerity/Phigments12",
+  "_name_or_path": "liminerity/merge6",
   "architectures": [
     "PhiForCausalLM"
   ],
@@ -23,7 +23,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
   "use_cache": true,
   "vocab_size": 51200

model.safetensors.index.json

@@ -1,460 +1 @@
-{
-  "metadata": {
-    "total_size": 11118735360
-  },
-  "weight_map": {
-    "lm_head.bias": "model-00003-of-00003.safetensors",
-    "lm_head.weight": "model-00003-of-00003.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
-    "model.final_layernorm.bias": "model-00003-of-00003.safetensors",
-    "model.final_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.12.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.22.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.22.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.23.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.23.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.24.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.24.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.25.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.25.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.25.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.26.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.26.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.26.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.27.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.27.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.27.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.28.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.28.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.28.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.29.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.29.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.30.input_layernorm.bias": "model-00003-of-00003.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.fc1.bias": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.fc1.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.fc2.bias": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.fc2.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.dense.bias": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.dense.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.fc1.bias": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.fc1.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.fc2.bias": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.fc2.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.dense.bias": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.dense.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors"
-  }
-}
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.final_layernorm.weight": "model-00001-of-00003.safetensors", "model.final_layernorm.bias": "model-00001-of-00003.safetensors", "model.layers.29.mlp.fc2.weight": "model-00001-of-00003.safetensors", "model.layers.29.mlp.fc2.bias": "model-00001-of-00003.safetensors", "model.layers.29.mlp.fc1.weight": "model-00001-of-00003.safetensors", "model.layers.29.mlp.fc1.bias": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.dense.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.dense.bias": "model-00001-of-00003.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.29.input_layernorm.bias": "model-00001-of-00003.safetensors", "model.layers.28.mlp.fc2.weight": "model-00001-of-00003.safetensors", "model.layers.28.mlp.fc2.bias": "model-00001-of-00003.safetensors", "model.layers.28.mlp.fc1.weight": "model-00001-of-00003.safetensors", "model.layers.28.mlp.fc1.bias": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.dense.weight": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.dense.bias": "model-00001-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.28.input_layernorm.bias": "model-00001-of-00003.safetensors", "model.layers.27.mlp.fc2.weight": "model-00001-of-00003.safetensors", "model.layers.27.mlp.fc2.bias": "model-00001-of-00003.safetensors", "model.layers.27.mlp.fc1.weight": "model-00001-of-00003.safetensors", "model.layers.27.mlp.fc1.bias": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.dense.weight": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.dense.bias": "model-00001-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.27.input_layernorm.bias": "model-00001-of-00003.safetensors", "model.layers.26.mlp.fc2.weight": "model-00001-of-00003.safetensors", "model.layers.26.mlp.fc2.bias": "model-00001-of-00003.safetensors", "model.layers.26.mlp.fc1.weight": "model-00001-of-00003.safetensors", "model.layers.26.mlp.fc1.bias": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.dense.weight": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.dense.bias": "model-00001-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.26.input_layernorm.bias": "model-00001-of-00003.safetensors", "model.layers.25.mlp.fc2.weight": "model-00001-of-00003.safetensors", "model.layers.25.mlp.fc2.bias": "model-00001-of-00003.safetensors", "model.layers.25.mlp.fc1.weight": "model-00001-of-00003.safetensors", "model.layers.25.mlp.fc1.bias": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.dense.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.dense.bias": "model-00001-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.25.input_layernorm.bias": "model-00001-of-00003.safetensors", "model.layers.24.mlp.fc2.weight": "model-00001-of-00003.safetensors", "model.layers.24.mlp.fc2.bias": "model-00001-of-00003.safetensors", "model.layers.24.mlp.fc1.weight": "model-00001-of-00003.safetensors", "model.layers.24.mlp.fc1.bias": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.dense.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.dense.bias": "model-00001-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.24.input_layernorm.bias": "model-00001-of-00003.safetensors", "model.layers.23.mlp.fc2.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.fc2.bias": "model-00001-of-00003.safetensors", "model.layers.23.mlp.fc1.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.fc1.bias": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.dense.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.dense.bias": "model-00001-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.23.input_layernorm.bias": "model-00001-of-00003.safetensors", "model.layers.22.mlp.fc2.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.fc2.bias": "model-00001-of-00003.safetensors", "model.layers.22.mlp.fc1.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.fc1.bias": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.dense.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.dense.bias": "model-00001-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.22.input_layernorm.bias": "model-00001-of-00003.safetensors", "model.layers.21.mlp.fc2.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.fc2.bias": "model-00001-of-00003.safetensors", "model.layers.21.mlp.fc1.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.fc1.bias": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.dense.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.dense.bias": "model-00001-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.input_layernorm.bias": "model-00001-of-00003.safetensors", "model.layers.20.mlp.fc2.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.fc2.bias": "model-00001-of-00003.safetensors", "model.layers.20.mlp.fc1.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.fc1.bias": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.dense.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.dense.bias": "model-00001-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.input_layernorm.bias": "model-00001-of-00003.safetensors", "model.layers.19.mlp.fc2.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.fc2.bias": "model-00001-of-00003.safetensors", "model.layers.19.mlp.fc1.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.fc1.bias": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.dense.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.dense.bias": "model-00001-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.input_layernorm.bias": "model-00001-of-00003.safetensors", "model.layers.18.mlp.fc2.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.fc2.bias": "model-00001-of-00003.safetensors", "model.layers.18.mlp.fc1.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.fc1.bias": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.dense.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.dense.bias": "model-00001-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.18.input_layernorm.bias": "model-00001-of-00003.safetensors", "model.layers.17.mlp.fc2.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.fc2.bias": "model-00001-of-00003.safetensors", "model.layers.17.mlp.fc1.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.fc1.bias": "model-00001-of-00003.safetensors", "lm_head.weight": "model-00002-of-00003.safetensors", "lm_head.bias": "model-00002-of-00003.safetensors", "model.layers.31.mlp.fc2.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.fc2.bias": "model-00002-of-00003.safetensors", "model.layers.31.mlp.fc1.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.fc1.bias": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.dense.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.dense.bias": "model-00002-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.31.input_layernorm.bias": "model-00002-of-00003.safetensors", "model.layers.30.mlp.fc2.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.fc2.bias": "model-00002-of-00003.safetensors", "model.layers.30.mlp.fc1.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.fc1.bias": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.dense.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.dense.bias": "model-00002-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.30.input_layernorm.bias": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.dense.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.dense.bias": "model-00002-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors", "model.layers.16.mlp.fc2.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.fc2.bias": "model-00002-of-00003.safetensors", "model.layers.16.mlp.fc1.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.fc1.bias": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.dense.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.dense.bias": "model-00002-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors", "model.layers.15.mlp.fc2.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.fc2.bias": "model-00002-of-00003.safetensors", "model.layers.15.mlp.fc1.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.fc1.bias": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.dense.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.dense.bias": "model-00002-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors", "model.layers.14.mlp.fc2.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.fc2.bias": "model-00002-of-00003.safetensors", "model.layers.14.mlp.fc1.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.fc1.bias": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.dense.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.dense.bias": "model-00002-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.14.input_layernorm.bias": "model-00002-of-00003.safetensors", "model.layers.13.mlp.fc2.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.fc2.bias": "model-00002-of-00003.safetensors", "model.layers.13.mlp.fc1.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.fc1.bias": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.dense.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.dense.bias": "model-00002-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.13.input_layernorm.bias": "model-00002-of-00003.safetensors", "model.layers.12.mlp.fc2.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.fc2.bias": "model-00002-of-00003.safetensors", "model.layers.12.mlp.fc1.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.fc1.bias": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.dense.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.dense.bias": "model-00002-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.12.input_layernorm.bias": "model-00002-of-00003.safetensors", "model.layers.11.mlp.fc2.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.fc2.bias": "model-00002-of-00003.safetensors", "model.layers.11.mlp.fc1.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.fc1.bias": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.dense.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.dense.bias": "model-00002-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.11.input_layernorm.bias": "model-00002-of-00003.safetensors", "model.layers.10.mlp.fc2.weight": "model-00002-of-00003.safetensors", "model.layers.10.mlp.fc2.bias": "model-00002-of-00003.safetensors", "model.layers.10.mlp.fc1.weight": "model-00002-of-00003.safetensors", "model.layers.10.mlp.fc1.bias": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.dense.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.dense.bias": "model-00002-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.10.input_layernorm.bias": "model-00002-of-00003.safetensors", "model.layers.9.mlp.fc2.weight": "model-00002-of-00003.safetensors", "model.layers.9.mlp.fc2.bias": "model-00002-of-00003.safetensors", "model.layers.9.mlp.fc1.weight": "model-00002-of-00003.safetensors", "model.layers.9.mlp.fc1.bias": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.dense.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.dense.bias": "model-00002-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.9.input_layernorm.bias": "model-00002-of-00003.safetensors", "model.layers.8.mlp.fc2.weight": "model-00002-of-00003.safetensors", "model.layers.8.mlp.fc2.bias": "model-00002-of-00003.safetensors", "model.layers.8.mlp.fc1.weight": "model-00002-of-00003.safetensors", "model.layers.8.mlp.fc1.bias": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.dense.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.dense.bias": "model-00003-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.8.input_layernorm.bias": "model-00003-of-00003.safetensors", "model.layers.7.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.layers.7.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.layers.7.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.layers.7.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.dense.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.dense.bias": "model-00003-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.7.input_layernorm.bias": "model-00003-of-00003.safetensors", "model.layers.6.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.layers.6.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.layers.6.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.layers.6.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.dense.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.dense.bias": "model-00003-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.6.input_layernorm.bias": "model-00003-of-00003.safetensors", "model.layers.5.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.layers.5.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.layers.5.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.layers.5.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.dense.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.dense.bias": "model-00003-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.5.input_layernorm.bias": "model-00003-of-00003.safetensors", "model.layers.4.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.layers.4.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.layers.4.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.layers.4.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.dense.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.dense.bias": "model-00003-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.4.input_layernorm.bias": "model-00003-of-00003.safetensors", "model.layers.3.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.layers.3.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.layers.3.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.layers.3.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.dense.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.dense.bias": "model-00003-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.3.input_layernorm.bias": "model-00003-of-00003.safetensors", "model.layers.2.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.layers.2.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.layers.2.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.layers.2.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.dense.weight": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.dense.bias": "model-00003-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.2.input_layernorm.bias": "model-00003-of-00003.safetensors", "model.layers.1.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.layers.1.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.layers.1.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.layers.1.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.dense.weight": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.dense.bias": "model-00003-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.1.input_layernorm.bias": "model-00003-of-00003.safetensors", "model.layers.0.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.layers.0.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.layers.0.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.layers.0.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.dense.weight": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.dense.bias": "model-00003-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.0.input_layernorm.bias": "model-00003-of-00003.safetensors", "model.embed_tokens.weight": "model-00003-of-00003.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,323 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}