TinyPixel/elm-test
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: TinyPixel/elm-test
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-12 04:43:17 +08:00
commit 0d0b7caccf
38 changed files with 94239 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

14
README.md Normal file
View File

@@ -0,0 +1,14 @@
# [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_TinyPixel__elm-test)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 43.74 |
| ARC (25-shot) | 53.16 |
| HellaSwag (10-shot) | 78.98 |
| MMLU (5-shot) | 47.04 |
| TruthfulQA (0-shot) | 39.51 |
| Winogrande (5-shot) | 74.35 |
| GSM8K (5-shot) | 7.51 |
| DROP (3-shot) | 5.65 |

27
config.json Normal file
View File

@@ -0,0 +1,27 @@
{
"_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"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": "bfloat16",
"transformers_version": "4.34.0.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": "4.34.0.dev0"
}

3
model-00001-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:45e183bec2158dede0d35811e5f30e551ff34fb4e1eb1b1b8f0118f3c54812cc
size 981485368

3
model-00002-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3455cd941e441f26bf6cab33dcb578b8499d6481d2eb6c0bf71e678e372b4cd2
size 966838864

3
model-00003-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:29ae5d994cc8fdf757b270d5bc8144970f5cad4332fcea0a40a54c0945ff4c2e
size 966822256

3
model-00004-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:90dd12b9f8bfc4a683a925a3bc493d3049e06cb9a85515e2fde46f90295a52d1
size 989907416

3
model-00005-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7f5a4e3c487b6a34e7f62f0f1e778ab6a16eb1f009bda4951d94f4614163e561
size 943753712

3
model-00006-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:47e1669ec75f78767fb4c83fdb918dc8ad8a4a0901496913cd9b2fc52eaf8943
size 989890824

3
model-00007-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4d2cf8e4d8692fc8d687eb6ed07270506ead0c856c756b1d1968216fe28dd588
size 966838888

3
model-00008-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fe194fb3471c4f172843e79869c7b10330671fe70045a179652632754a09b294
size 966822272

3
model-00009-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c82d4ac25998afa6451822e9ff964aa52422eb841e4eb80eae78412da5050f8b
size 989907440

3
model-00010-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9c1f0dcd1623bd7d500cbba1812e64f4807cadc7e2be4884d0bd0f5a624b8802
size 943753720

3
model-00011-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2409097dc2287a34303897055716068d737439563b77da8cb6ddd8c36b9ffa33
size 989890824

3
model-00012-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:016a721dab1d963e8b37ed788a440f350d852dab78ccef86025cc9125712ba54
size 966838888

3
model-00013-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:486b35e8e7e67180e671da65f2fbe22128e2c027da87fdbfec0af6ec74456c82
size 966822272

3
model-00014-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:92e01dc2c09c58dd796aa76c885c87eca3fbfacbf84fdb89f0e1d600b2d9e36a
size 847292072

298
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,298 @@
{
"metadata": {
"total_size": 13476831232
},
"weight_map": {
"lm_head.weight": "model-00014-of-00014.safetensors",
"model.embed_tokens.weight": "model-00001-of-00014.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.input_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.10.input_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.11.input_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.12.input_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.13.input_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.14.input_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.15.input_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.16.input_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.17.input_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.18.input_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.19.input_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.20.input_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.21.input_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.22.input_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.23.input_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.24.input_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.25.input_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.26.input_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.27.input_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.28.input_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.29.input_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.30.input_layernorm.weight": "model-00014-of-00014.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.31.input_layernorm.weight": "model-00014-of-00014.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.4.input_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.5.input_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.6.input_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.7.input_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.8.input_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.9.input_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
"model.norm.weight": "model-00014-of-00014.safetensors"
}
}

3
pytorch_model-00001-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:de84efac4c57ffe4c042f2129c2ff322365bb011109c6160f4466cefe4a0cb7b
size 981489327

3
pytorch_model-00002-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d8f35caba611974011f71904981e7f3d92ae4b2b4c0520645caf3904a06bb906
size 966844269

3
pytorch_model-00003-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0aaf1ae5308a230d5434210778c82d33246a016b239bd3b6ae6c37cd8caedeb0
size 966827273

3
pytorch_model-00004-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f66e1a803720e8dc47144da843462f11292f2e31c31d542ea8335d0872c4ceeb
size 989912603

3
pytorch_model-00005-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:654b3112695181a6ce172186d107cfbaac7806ca19d59c7ad3672f0327eb8245
size 943758939

3
pytorch_model-00006-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7f7c40a29fd6d845db1345f41aad01254ba05ea300024f2955ba0aeb92298407
size 989895607

3
pytorch_model-00007-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9801ac013570d430e8d7bd04e2fa17f23bf2a6ee7e132d3eeeb8fcb38dd90e76
size 966844269

3
pytorch_model-00008-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:121cf46e7a4b6d55bddd7d75f2e9980aa0babcac1488bad34187aa1d80f7cc83
size 966827273

3
pytorch_model-00009-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9af527b1730d4aecef2cc7dc58144626a03c07750c3018034225e2f057f09217
size 989912667

3
pytorch_model-00010-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cfc416250b40dfa7afd21e27c27b5fce84bc276afb2b1279cbf8dc50e1ac85b6
size 943758939

3
pytorch_model-00011-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5ea9b53e1a6a4ea1af52a4f2057f9f912879f41034486046229303a6737ab0f6
size 989895607

3
pytorch_model-00012-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4f499fb59549207623f23091a8c9608be854e77b6518da9dc726250d85842448
size 966844269

3
pytorch_model-00013-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a2f41748d66168a343568eab59796deaacfb52ef1d0d407d366d351834b2d5f1
size 966827273

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a2bebb368b3296050f97f6027042b502a456eca5da8bb421a76c2c17abf3d8c7
size 847295773

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

@@ -0,0 +1,298 @@
{
"metadata": {
"total_size": 13476831232
},
"weight_map": {
"lm_head.weight": "pytorch_model-00014-of-00014.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.10.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.12.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.14.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.16.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.18.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.19.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.20.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.21.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.23.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.24.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.25.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.26.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.28.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.30.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.31.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.norm.weight": "pytorch_model-00014-of-00014.bin"
}
}

6
special_tokens_map.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token": "<s>",
"eos_token": "</s>",
"pad_token": "</s>",
"unk_token": "<unk>"
}

93423
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

44
tokenizer_config.json Normal file
View File

@@ -0,0 +1,44 @@
{
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": null,
"max_length": 1024,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"stride": 0,
"tokenizer_class": "LlamaTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>",
"use_default_system_prompt": true
}