初始化项目，由ModelHub XC社区提供模型

Model: vihangd/smartyplats-3b-v2
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 +1,17 @@
+---
+license: apache-2.0
+---
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vihangd__smartyplats-3b-v2)
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 35.3   |
+| ARC (25-shot)         | 41.04          |
+| HellaSwag (10-shot)   | 71.19    |
+| MMLU (5-shot)         | 24.32         |
+| TruthfulQA (0-shot)   | 36.66   |
+| Winogrande (5-shot)   | 66.93   |
+| GSM8K (5-shot)        | 1.59        |
+| DROP (3-shot)         | 5.39         |

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "openlm-research/open_llama_3b_v2",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 3200,
+  "initializer_range": 0.02,
+  "intermediate_size": 8640,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.33.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.33.1"
+}

pytorch_model-00001-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e7ad5a12d7a5b9e48183932225d666035b79530e3e0147fc67a40d3cf979506
+size 397314832

pytorch_model-00002-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96cb1662345d6a50693f5b3858189bd7e8d17cdecb829f70d70abdc666507a7f
+size 385055215

pytorch_model-00003-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3efa75699d91213914381b3c1e9f5b4c4839f85c83a83fd2d4a37a12f160c173
+size 358416853

pytorch_model-00004-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20c2640bd981ca9845276a66076e31dba1a126fe7564e74d1c09490c59f400ff
+size 385055215

pytorch_model-00005-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:532f730e46f6cb306a3d8c7192ee8d1bfe61b3b9ddc1acab6c05dc1011a3f8cd
+size 358416853

pytorch_model-00006-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a424da1470e0e20308545adf248cfcfa25162940da82e6602db1a4815c154d87
+size 385055215

pytorch_model-00007-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8080db443bf3950587126be0111e4cfc0f855db2142e7b79d503e6e4fe807efb
+size 358416853

pytorch_model-00008-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:249c2046e9095b070d0ef5b6872e79dda4fdf40429129ca5d8ea653a0a8ea269
+size 385055215

pytorch_model-00009-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a6eb31ebdbab3ad707d47de667d050c4b77e32fc9024b29309fcdc255c8a504
+size 358416853

pytorch_model-00010-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:449ca997395e6f5b1b546cfc59d216af6343f4ad67015382ba41a5433377239e
+size 385055215

pytorch_model-00011-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bef17d98e38fd2ba385146179f69bf0b4f82fe71af3d1c3fcaf9c24f669c1c5
+size 358416853

pytorch_model-00012-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462854056c8af62eb9dc9422f38b1f130ea2f3858a9155f2478b53a1dcc52ba6
+size 385055215

pytorch_model-00013-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9501df0a1aaecc093db0d9944a37bcd597abe49d4686449eb4a323ac06758edc
+size 358416853

pytorch_model-00014-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3282cea77d4021e98dd41c910d5920a01f28255bdf42aaa8005ad389409a0cb0
+size 385055215

pytorch_model-00015-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f32c4c0668f9c9a45ee026ac74d730cead06cee3584c386c0fc1f4c452a22f1e
+size 358416853

pytorch_model-00016-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feba35cff2ab31a9e1ca23bb52e89d7dd788de9faac5bb8bce921103bcf6cf77
+size 385055215

pytorch_model-00017-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b3c5c9b895202407455d7b84ce87fdb77e0809b3abadf9258c9a18cabb79d4
+size 358416853

pytorch_model-00018-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5145376a9a1ff8fcc4b58a72b79ca649d41d6286b77d72fd3b03dbdc97cf27f6
+size 303140665

pytorch_model-00019-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a17055b85ca12ecda0f8d3496084fa7650d0812284141e4f7fef64880a1d9c54
+size 204800938

pytorch_model.bin.index.json

@@ -0,0 +1,244 @@
+{
+  "metadata": {
+    "total_size": 6852947200
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00019-of-00019.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00019.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00019.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00019.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00019.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00019.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00019.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00019.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.norm.weight": "pytorch_model-00018-of-00019.bin"
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
+size 511574

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}