axiong/PMC_LLaMA_13B
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: axiong/PMC_LLaMA_13B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-04 21:01:24 +08:00
commit 0fafc01b68
17 changed files with 46564 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

41
README.md Normal file
View File

@@ -0,0 +1,41 @@
---
license: openrail
---
# PMC_LLaMA
To obtain the foundation model in medical field, we propose [MedLLaMA_13B](https://huggingface.co/chaoyi-wu/MedLLaMA_13B) and PMC_LLaMA_13B.
MedLLaMA_13B is initialized from LLaMA-13B and further pretrained with medical corpus. Despite the expert knowledge gained, it lacks instruction-following ability.
Hereby we construct a instruction-tuning dataset and evaluate the tuned model.
As shown in the table, PMC_LLaMA_13B achieves comparable results to ChatGPT on medical QA benchmarks.
![medical_qa](https://pic4.zhimg.com/80/v2-bf43393cd753018e11fdb1c64a1a87df.png)
## Usage
```python
import transformers
import torch
tokenizer = transformers.LlamaTokenizer.from_pretrained('axiong/PMC_LLaMA_13B')
model = transformers.LlamaForCausalLM.from_pretrained('axiong/PMC_LLaMA_13B')
sentence = 'Hello, doctor'
batch = tokenizer(
sentence,
return_tensors="pt",
add_special_tokens=False
)
with torch.no_grad():
generated = model.generate(
inputs = batch["input_ids"],
max_length=200,
do_sample=True,
top_k=50
)
print('model predict: ',tokenizer.decode(generated[0]))
```

3
added_tokens.json Normal file
View File

@@ -0,0 +1,3 @@
{
"[PAD]": 32000
}

24
config.json Normal file
View File

@@ -0,0 +1,24 @@
{
"_name_or_path": "/home/cs/leijiayu/wuchaoyi/LLaMA_MedFinetune",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 0,
"eos_token_id": 1,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 2048,
"max_sequence_length": 2048,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"pad_token_id": -1,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.28.1",
"use_cache": true,
"vocab_size": 32001
}

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 0,
"eos_token_id": 1,
"pad_token_id": 0,
"transformers_version": "4.28.1"
}

3
pytorch_model-00001-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:672d429d82d62e0b164f85088def2f63b7f57077124084ee97bc658cf56a57ee
size 9956564427

3
pytorch_model-00002-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e09585976977e6991e7e37edaee1bff4c988f4ed3c69c522f87cc90164f50729
size 9940856577

3
pytorch_model-00003-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e15ef6b421695358d7b2232493ef629d7851947ba3a02ed6b3675c37fa169543
size 9940857007

3
pytorch_model-00004-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aa3e34da0800635ee8c85b187fcf2ca067ac516f3df6f1198a7a4097b38cb90a
size 9867415353

3
pytorch_model-00005-of-00006.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5059737714168f144c1140dd5b2c382d6a2c547415eb7bf64b44d7ab431d9595
size 9867457089

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:44101de2d5d2ee19f5fabf42c192640d36cb5a56cb5122e40fb3a0ad7cf1b195
size 2490496751

410
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,410 @@
{
"metadata": {
"total_size": 52063503360
},
"weight_map": {
"lm_head.weight": "pytorch_model-00006-of-00006.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
"model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
"model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
"model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
"model.norm.weight": "pytorch_model-00006-of-00006.bin"
}
}

6
special_tokens_map.json Normal file
View File

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

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

Binary file not shown.

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": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"pad_token": null,
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"use_fast": false
}

45979
trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1e90be6ce830ad44c2a041161d0d228cfc6b10d21ab320230a2452e57a94d7ac
size 3899