vihangd/shearedplats-2.7b-v2
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: vihangd/shearedplats-2.7b-v2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-18 22:16:16 +08:00
commit 8f2df1b670
23 changed files with 93868 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -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

26
README.md Normal file
View File

@@ -0,0 +1,26 @@
---
license: llama2
---
<p><h1> ShearedPlats-7b </h1></p>
An experimental finetune of Sheared LLaMA 2.7b with Alpaca-QLoRA (version 2)
<h2> Datasets </h2>
Trained on alpca style datasets
<p><h2> Prompt Template </h2></p>
Uses alpaca style prompt template
<br/>
# [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__shearedplats-2.7b-v2)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 36.72 |
| ARC (25-shot) | 42.41 |
| HellaSwag (10-shot) | 72.58 |
| MMLU (5-shot) | 27.52 |
| TruthfulQA (0-shot) | 39.76 |
| Winogrande (5-shot) | 65.9 |
| GSM8K (5-shot) | 1.52 |
| DROP (3-shot) | 7.34 |

28
config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"_name_or_path": "princeton-nlp/Sheared-LLaMA-2.7B",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 6912,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 20,
"num_hidden_layers": 32,
"num_key_value_heads": 20,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.35.0.dev0",
"use_cache": true,
"vocab_size": 32000
}

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.35.0.dev0"
}

3
pytorch_model-00001-of-00015.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:15f44b392b620a3016c602301c1dc558b2cdc1f45156edd5df07b1127880be74
size 374881638

3
pytorch_model-00002-of-00015.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:65feeee6ac5743e085d5acab96801af6a9b6a909108b4a9c69142ec3e4e5a696
size 388000914

3
pytorch_model-00003-of-00015.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2f9dd7591d488c0f714b5020379c92693f8d80d258c0fcf3d43398d1b5f46153
size 391944602

3
pytorch_model-00004-of-00015.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cc8c22775802df355664ee8790ba1a407590bf94d38ecb209e640ac9290eda30
size 365718674

3
pytorch_model-00005-of-00015.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2b657cf41e0d68ef99e34e5df213a6df5db689a772e492e33965a926e01ce6fa
size 388011830

3
pytorch_model-00006-of-00015.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9d0a64996a77da86f6d398357ee2f7fbbfe365b6884778ba091a3b41b13fcba7
size 369651510

3
pytorch_model-00007-of-00015.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1ec3b65d0c5d290f8cadd0545f29d053482b8047c27066fcac1b822569df2f58
size 388000978

3
pytorch_model-00008-of-00015.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8a0918c8318106145467f983feb1a80d002082004f2047def8d82ee8fe2dcc96
size 391944602

3
pytorch_model-00009-of-00015.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:05543a9c923ae6b8ca89aa0f5f02d6bb79cfc8e03d4199078c1106472b23aa21
size 365718738

3
pytorch_model-00010-of-00015.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7dcfdc84f53d1f75480f9cdecf447aecd0cabe50e559b49e7cccdc18c51ceac2
size 388011830

3
pytorch_model-00011-of-00015.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cc3d8bbcbc4b75e9c0b2c1c89b1ae8cab26a51ecba11ef27b636e81de49825e5
size 369651510

3
pytorch_model-00012-of-00015.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b80a3eedb999ec6f6cff394d6f875645d6f31a3b22df8533f32518a71f9b64e8
size 388000978

3
pytorch_model-00013-of-00015.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2afe806b012aaaf6736be7fa595897325f3ca45de106f81bfce44884938f6091
size 391944602

3
pytorch_model-00014-of-00015.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:74888cd30892d04c816fbfb207f869daa264b7ffbb5f9bb74ffbaf9737afe25a
size 277904330

3
pytorch_model-00015-of-00015.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0edd18c223a83ab8026c2079b9b31dc28c1cddcf135da16d684bae271e83392c
size 163841413

298
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,298 @@
{
"metadata": {
"total_size": 5403120640
},
"weight_map": {
"lm_head.weight": "pytorch_model-00015-of-00015.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
"model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
"model.layers.10.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.12.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
"model.layers.14.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.15.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
"model.layers.16.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.17.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.18.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
"model.layers.19.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.20.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
"model.layers.21.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.22.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
"model.layers.23.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.24.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.25.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
"model.layers.26.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.27.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
"model.layers.28.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.29.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
"model.layers.30.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
"model.layers.31.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
"model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
"model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
"model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
"model.norm.weight": "pytorch_model-00014-of-00015.bin"
}
}

93391
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
size 499723

35
tokenizer_config.json Normal file
View File

@@ -0,0 +1,35 @@
{
"add_bos_token": true,
"add_eos_token": false,
"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
}
}