Upload folder using huggingface_hub

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "NousResearch/Nous-Hermes-2-Yi-34B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.0.dev0"
+}

pytorch_model-00001-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54cfff6ee41f8b783c443b6e894aca0a04af4a1048f43673fa051cc0d295519f
+size 4793138393

pytorch_model-00002-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e4a79ccc505396123241833b9d1220a4ac22bc4c4ba30cb926c7f3d96ee9df5
+size 4756468297

pytorch_model-00003-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e0e38449c15586cf473f4c780f5f4d20298fab0d784d97645ddcf9100af11a7
+size 4991380097

pytorch_model-00004-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ed92b711e556433bce074c4421da3161a6ff5dc049781adbe7376477894966
+size 4756468333

pytorch_model-00005-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ad4776ba49040b895378a27de17bb4514222224a684d107ec0749257b3122ba
+size 4756468297

pytorch_model-00006-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a9aa330738401cc14f681d0ad2f30bc8f54ae0a2488b8db4a53427f2aff9ad
+size 4991380161

pytorch_model-00007-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acffbb4a1760de6b952c4c30763663f8bcae83a15fc55a35817751a665b93d8d
+size 4756468333

pytorch_model-00008-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90609ccad54ad6785de8cd26e963a0c9c4f5a1c416f08287536843d4b0989bc1
+size 4756468297

pytorch_model-00009-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33327e0a3b01a3c20cbaddd90148de0b5fea66e0703904fd257e98d85865ebf
+size 4991380161

pytorch_model-00010-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f52dc9a2f6d4c4a59f5498def1f289ea657b971182ff7a5a0a92b9712c2ba7
+size 4756468333

pytorch_model-00011-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b26139b0205020484d81d0e644ad2a8da3290cda3153b51641c4f3feabc7cee
+size 4756468297

pytorch_model-00012-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27587dfb24188a0352a2b08624d4f4c4fcd700c88e6da6bc566d1d15e82c0a3d
+size 4991380161

pytorch_model-00013-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e20fce85bf47d48f83b18c91789f8fab08130b0c68e2373eeb72818108a7751
+size 4756468333

pytorch_model-00014-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab5c8bcee01b240348d0218f20c96b0f6e03082deb73518373fddc5aa8043bc
+size 4756468297

pytorch_model-00015-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43954c0864e3664795ccdef1fc307d1248a2e75ea0d528050d6775533d348d69
+size 1211150446

pytorch_model.bin.index.json

@@ -0,0 +1,550 @@
+{
+  "metadata": {
+    "total_size": 68777834496
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00015-of-00015.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.56.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.59.input_layernorm.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.norm.weight": "pytorch_model-00015-of-00015.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}