Upload folder using huggingface_hub (#3)

- 9ddcc45d468abf777e323567280f4d3941fc02a74bbe95d3f3a3ad0137e8bce2 (76f6d781927159047e84b65de5a2feadaa3ee456)
- 509cec288324654e16d1efe4351a8b4133dd44070cd18a31d7db5084a02e373d (065b8c04b6e712b60d7bafc5265ec27c144161f0)
- 37310120d481921944de9c99b5c63cbc1fc67608d232f909944f7320ebe10e38 (d10f2cd927d93e31e5f88bedac5458cfe4b11a80)
- a0ea024ff64511e03d7cce1ea71d7df6405afd0a567a2c16fc0d8866227e45bd (89feede65e54bed57e7699016afb159964047468)
- e7968b9b1189e4dd313c701f7e00cb12618bdeea4f77e503cbc20ac11dc1ade6 (a1cb860a780e57507cdd2bfd38d2ff5c2958dceb)
- 129a675e4dfeb6b62cafcd121910411396146ae447aa8c11a2da60effac92cab (c1f9ebaf0fa6c40ed1de67fd3f808ed2e0b03167)

config.json

@@ -1,26 +1,26 @@
-{
-  "architectures": [
-    "MistralForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "head_dim": 128,
-  "hidden_act": "silu",
-  "hidden_size": 5120,
-  "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 1024000,
-  "model_type": "mistral",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 40,
-  "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-05,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.43.3",
-  "use_cache": false,
-  "vocab_size": 131073
-}
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.3",
+  "use_cache": false,
+  "vocab_size": 131073
+}

generation_config.json

@@ -1,7 +1,7 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "do_sample": true,
-  "eos_token_id": 2,
-  "transformers_version": "4.43.3"
-}
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.43.3"
+}

model-00001-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecee12ed9774526f609db52140308b3589510a938a056d0cb5ee56d13792a6d9
-size 4865532672
+oid sha256:3b59e0b57bb2ce5cdca7379b0607a7beca23a9a93429f2b132fa42d3361e498b
+size 4865532736

model-00002-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c44a4155fb3a6aabe24533433ecccf253757a6045e59d030305f83b007943e
-size 4907529344
+oid sha256:12ed4cfbeee865f89d1f8232bc0f8947a81ce85410de84650b56dd088c6b8705
+size 4907529424

model-00003-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a35f8762a4227ac588681b1ee864367cb57759ee637b1d046e217c15e9060b5
-size 4907529376
+oid sha256:3b2384fb9dbea4d41068236bdd4ef45a597e5e7736dfb1b2c5e62ad6a07bcba2
+size 4907529456

model-00004-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50ab377ec8d76c8cf94bd8f93760da28645e22913b9f7e611385962e6fe61db9
-size 4907529376
+oid sha256:835ff4f33dc35eddc23ed03d73a8a26d72fcd217aafb338d8bdc82231fb6af61
+size 4907529456

model-00005-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e251bd35ba3abc0ec7f0cb4713b2d3cb84888885a85491b499c3183b54bd8986
-size 4907506448
+oid sha256:904d47cde55cc35f158a55635977e847bfeab358a6a1432b95440830481aa5b3
+size 4907506512

model.safetensors.index.json

@@ -1,370 +1,370 @@
-{
-  "metadata": {
-    "total_size": 24495585280
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00005-of-00005.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.norm.weight": "model-00005-of-00005.safetensors"
-  }
-}
+{
+  "metadata": {
+    "total_size": 24495585280
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

special_tokens_map.json

@@ -1,30 +1,30 @@
-{
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}