Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,21 @@
+{
+  "<CLS>": 32000,
+  "<EOD>": 32002,
+  "<MASK>": 32003,
+  "<PAD>": 32004,
+  "<SEP>": 32001,
+  "<|im_end|>": 32018,
+  "<|im_start|>": 32017,
+  "[/bib]": 32010,
+  "[/bib_ref]": 32006,
+  "[/fig]": 32012,
+  "[/fig_ref]": 32008,
+  "[/formula]": 32016,
+  "[/table]": 32014,
+  "[bib]": 32009,
+  "[bib_ref]": 32005,
+  "[fig]": 32011,
+  "[fig_ref]": 32007,
+  "[formula]": 32015,
+  "[table]": 32013
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32019
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.2"
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83b75d8300b44e680634f19e1cb22fcc31cb74c736cf7d6d3941c29066795df3
+size 1914925352

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68b365b72cc213194eb7e2e87cdbc5f217c024808845307d5bb9df7a0db1a59
+size 1900089976

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942311c132cdde14262902cf058dd1d01c25acc65bfe6b6a4e95efb548d0f94e
+size 1843483520

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:087358619cfa61ae73b799eb6c60002840e8c78cc9de9e5d6fbe64f9a162b7d7
+size 1923175184

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5a61963bf428feec7e8e98b8c0181accd2cde52af32a683e9157cce1ad9b099
+size 1900090016

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78a336f90165d9af12001eeee7bb2234031abfe35f4aca3ad5dd25a4bcf173ff
+size 1843483528

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2960cc1e29f415b374f9e765685738e771fa4ead67e914e5271069ec7f02faa5
+size 1889628920

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a050afefa51b83daa43c66f5ec398ace1186708b9318dea79965a8d362605aff
+size 262299776

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13477142528
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00008-of-00008.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.norm.weight": "model-00007-of-00008.safetensors"
+  }
+}

pytorch_model-00001-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f29ca7c8f199789c06e42e2f89add708e3b674669591732fd99d677271823075
+size 1914777979

pytorch_model-00002-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea67a368f839c46c92fc05dda97bc2ceeb2cc66301d0879f1ec861c0847c3731
+size 1900098929

pytorch_model-00003-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bebaa16b57d0fbea5801cc546d7d8bad5dd7c6c911109cef8af8fb31f6e5107
+size 1843492885

pytorch_model-00004-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3500e97fcacf7edef5326571c0833f5139d8fa38c7782dec338f7adf2c1ed30
+size 1923184323

pytorch_model-00005-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adb46e8b68767fe7d7751c599d66e420ffe81cfd02acac4d92847446499671bc
+size 1900098993

pytorch_model-00006-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6395771cc04d836d0d9b151293a9438e99a26d64613ba827de9c2f1023d1a3fb
+size 1843492949

pytorch_model-00007-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d9b8d1b12b518c7f378b25059a4b3a19ab3715c30e6de768afca328da869da
+size 1889638083

pytorch_model-00008-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27281e58640853b2c1f03eb0123f4ffbc783d8793cb151c082db6922cbfa4fa8
+size 262144938

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13476831232
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00008-of-00008.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.norm.weight": "pytorch_model-00007-of-00008.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "additional_special_tokens": [
+    "[bib_ref]",
+    "[/bib_ref]",
+    "[fig_ref]",
+    "[/fig_ref]",
+    "[bib]",
+    "[/bib]",
+    "[fig]",
+    "[/fig]",
+    "[table]",
+    "[/table]",
+    "[formula]",
+    "[/formula]",
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": "<CLS>",
+  "eos_token": "<|im_end|>",
+  "mask_token": "<MASK>",
+  "pad_token": "<PAD>",
+  "sep_token": "<SEP>",
+  "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,211 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<EOD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<MASK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "[bib_ref]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "[/bib_ref]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "[fig_ref]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "[/fig_ref]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "[bib]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "[/bib]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "[fig]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "[/fig]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "[table]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "[/table]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "[formula]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "[/formula]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[bib_ref]",
+    "[/bib_ref]",
+    "[fig_ref]",
+    "[/fig_ref]",
+    "[bib]",
+    "[/bib]",
+    "[fig]",
+    "[/fig]",
+    "[table]",
+    "[/table]",
+    "[formula]",
+    "[/formula]",
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS>",
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "mask_token": "<MASK>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sep_token": "<SEP>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}