初始化项目，由ModelHub XC社区提供模型

Model: andreaskoepf/llama2-13b-megacode2_min100
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,4 @@
+---
+license: other
+---
+- wandb: [run34_megacode2_min100_13b](https://wandb.ai/open-assistant/epfl-mt-sft/runs/run34_megacode2_min100_13b)

added_tokens.json

@@ -0,0 +1,9 @@
+{
+  "<CLS>": 32000,
+  "<EOD>": 32002,
+  "<MASK>": 32003,
+  "<PAD>": 32004,
+  "<SEP>": 32001,
+  "<|im_end|>": 32006,
+  "<|im_start|>": 32005
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 32005,
+  "eos_token_id": 32006,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 32007
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 32005,
+  "eos_token_id": 32006,
+  "pad_token_id": 0,
+  "transformers_version": "4.31.0"
+}

pytorch_model-00001-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68c2905e84622ab407e5d957c5db51e13bf56aeb2f893d5b640c53792be9902b
+size 3709532442

pytorch_model-00002-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ac2e52618efb80d24a77ef275cd9a987897956ed65a2b7bc07a35ab42878d8e
+size 3701617004

pytorch_model-00003-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027c243ae0dfcd3445b7a2ada510ebb6cc46c7eb0c7423bf529a6bf37f4de881
+size 3701617662

pytorch_model-00004-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a35b79e40a33abc4b1fb899ee5c935d37b3a51ad1fe8ea659705f2b24c4e33b
+size 3664896684

pytorch_model-00005-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20e26f0ccc5f7d77a21191d6b4352c1619a9752dabfddafcd8fb18de2f2a089a
+size 3664917840

pytorch_model-00006-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5d4c91832515da5f8382158343e7bdfdb388a50c8c96792c95906c4220f41cc
+size 3664917840

pytorch_model-00007-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58042fb65429539213c6a77f90f62e72b59b4086c1f00101acf2be89ad8e83f
+size 3596769306

pytorch_model-00008-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659119c0075b6d40340077da1b3f47ab043e0fa37cc1f2549a0226fad631cc5c
+size 327753093

pytorch_model.bin.index.json

@@ -0,0 +1,410 @@
+{
+  "metadata": {
+    "total_size": 26031882240
+  },
+  "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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-00002-of-00008.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-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-00002-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-00002-of-00008.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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-00003-of-00008.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-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.rotary_emb.inv_freq": "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-00003-of-00008.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-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.rotary_emb.inv_freq": "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-00004-of-00008.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-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.rotary_emb.inv_freq": "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-00004-of-00008.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-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.rotary_emb.inv_freq": "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-00006-of-00008.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-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-00001-of-00008.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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-00002-of-00008.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-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-00002-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.rotary_emb.inv_freq": "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-00002-of-00008.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.norm.weight": "pytorch_model-00007-of-00008.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "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_config.json

@@ -0,0 +1,33 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}