初始化项目，由ModelHub XC社区提供模型
Model: minlik/chinese-alpaca-33b-merged Source: Original Platform
This commit is contained in:
ModelHub XC
34
.gitattributes
vendored
Normal file
34
.gitattributes
vendored
Normal file
@@ -0,0 +1,34 @@
|
||||
*.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
|
||||
*.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
|
||||
76
README.md
Normal file
76
README.md
Normal file
@@ -0,0 +1,76 @@
|
||||
---
|
||||
title: chinese-alpaca-33b-merged
|
||||
emoji: 📚
|
||||
colorFrom: gray
|
||||
colorTo: red
|
||||
sdk: gradio
|
||||
sdk_version: 3.23.0
|
||||
app_file: app.py
|
||||
pinned: false
|
||||
---
|
||||
|
||||
加入中文词表并继续预训练中文Embedding，并在此基础上继续使用指令数据集finetuning，得到的中文Alpaca-33B模型。
|
||||
|
||||
模型转换用到的相关base及lora模型如下：
|
||||
- base-model: elinas/llama-30b-hf-transformers-4.29
|
||||
- lora-model: ziqingyang/chinese-alpaca-lora-33b
|
||||
|
||||
详情可参考：https://github.com/ymcui/Chinese-LLaMA-Alpaca/releases/tag/v4.0
|
||||
|
||||
|
||||
### 使用方法参考
|
||||
1. 安装模块包
|
||||
```bash
|
||||
pip install sentencepiece
|
||||
pip install transformers>=4.28.0
|
||||
```
|
||||
|
||||
2. 生成文本
|
||||
```python
|
||||
import torch
|
||||
import transformers
|
||||
from transformers import LlamaTokenizer, LlamaForCausalLM
|
||||
|
||||
def generate_prompt(text):
|
||||
return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
||||
|
||||
### Instruction:
|
||||
{text}
|
||||
|
||||
### Response:"""
|
||||
|
||||
|
||||
tokenizer = LlamaTokenizer.from_pretrained('minlik/chinese-alpaca-33b-merged')
|
||||
model = LlamaForCausalLM.from_pretrained('minlik/chinese-alpaca-33b-merged').half().to('cuda')
|
||||
model.eval()
|
||||
|
||||
text = '第一个登上月球的人是谁？'
|
||||
prompt = generate_prompt(text)
|
||||
input_ids = tokenizer.encode(prompt, return_tensors='pt').to('cuda')
|
||||
|
||||
|
||||
with torch.no_grad():
|
||||
output_ids = model.generate(
|
||||
input_ids=input_ids,
|
||||
max_new_tokens=128,
|
||||
temperature=1,
|
||||
top_k=40,
|
||||
top_p=0.9,
|
||||
repetition_penalty=1.15
|
||||
).cuda()
|
||||
output = tokenizer.decode(output_ids[0], skip_special_tokens=True)
|
||||
print(output.replace(prompt, '').strip())
|
||||
```
|
||||
# [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_minlik__chinese-alpaca-33b-merged)
|
||||
|
||||
| Metric | Value |
|
||||
|-----------------------|---------------------------|
|
||||
| Avg. | 53.09 |
|
||||
| ARC (25-shot) | 59.3 |
|
||||
| HellaSwag (10-shot) | 78.43 |
|
||||
| MMLU (5-shot) | 57.69 |
|
||||
| TruthfulQA (0-shot) | 52.45 |
|
||||
| Winogrande (5-shot) | 76.09 |
|
||||
| GSM8K (5-shot) | 8.04 |
|
||||
| DROP (3-shot) | 39.67 |
|
||||
22
config.json
Normal file
22
config.json
Normal file
@@ -0,0 +1,22 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 6656,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 17920,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 52,
|
||||
"num_hidden_layers": 60,
|
||||
"pad_token_id": 0,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.28.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 49954
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.28.1"
|
||||
}
|
||||
3
model-00001-of-00007.safetensors
Normal file
3
model-00001-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8966634a833bf2da6b24abb38fd1d44b553035395f87773a2f9c2752339d02f3
|
||||
size 9818757032
|
||||
3
model-00002-of-00007.safetensors
Normal file
3
model-00002-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c2b34de85e57d2456ff70afac56a955d2168f102132d8455b3731ed806824e88
|
||||
size 9869449648
|
||||
3
model-00003-of-00007.safetensors
Normal file
3
model-00003-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b4ec0d4a896e1591a8649c8b4e053de4006cca34585c195082c7307915fd0e99
|
||||
size 9958081304
|
||||
3
model-00004-of-00007.safetensors
Normal file
3
model-00004-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:588af3b0d702dff3288ca4b0c0a0ebba0cd592bdab961b2dd2f3a244d0a45394
|
||||
size 9896713232
|
||||
3
model-00005-of-00007.safetensors
Normal file
3
model-00005-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5793b9b39ede13f4fb3ca982ca7c430e937c2990a93cc34e2c47a36cebe8a4c6
|
||||
size 9869449664
|
||||
3
model-00006-of-00007.safetensors
Normal file
3
model-00006-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e6ac76d49018fee1d2ed2302e7d9fccba256d09bf973c6f0b20f83e16a64b9e
|
||||
size 9869449664
|
||||
3
model-00007-of-00007.safetensors
Normal file
3
model-00007-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d194bdac80a33e68cab62db5d0f4342e2677c4f17ad3356bab00d59c5597a290
|
||||
size 6254078336
|
||||
610
model.safetensors.index.json
Normal file
610
model.safetensors.index.json
Normal file
@@ -0,0 +1,610 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 65535909888
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00007-of-00007.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.36.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.37.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.38.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.39.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.40.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.41.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.42.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.43.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.44.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.45.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.46.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.47.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.48.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.49.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.50.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.51.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.52.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.53.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.54.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.55.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.56.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.57.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.58.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.59.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.norm.weight": "model-00007-of-00007.safetensors"
|
||||
}
|
||||
}
|
||||
3
pytorch_model-00001-of-00007.bin
Normal file
3
pytorch_model-00001-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e45840ddf877eca6bbda7f92bd0f494515c12cd0940a577c13055fcc3f9ca137
|
||||
size 9818776921
|
||||
3
pytorch_model-00002-of-00007.bin
Normal file
3
pytorch_model-00002-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b478503bcf29a78b0934b8788c9ceb32d0d7c6541689194b161d755dce5dee6e
|
||||
size 9869470445
|
||||
3
pytorch_model-00003-of-00007.bin
Normal file
3
pytorch_model-00003-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6224564338b03f9b3cc67fa65776b353897e6c9f387d534b8c73874dab719065
|
||||
size 9958102743
|
||||
3
pytorch_model-00004-of-00007.bin
Normal file
3
pytorch_model-00004-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ae131b6d299f8e4609c0c5269c310aa7d25c7fcc52f937bc4d8207f25525ff5e
|
||||
size 9896734715
|
||||
3
pytorch_model-00005-of-00007.bin
Normal file
3
pytorch_model-00005-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ab515436edd7ad27d0e86eb84d6565639c30b744ee3e0977474d5191a1f653ce
|
||||
size 9869470481
|
||||
3
pytorch_model-00006-of-00007.bin
Normal file
3
pytorch_model-00006-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b17bc0f74c3913eccbf2a9711a398f9d434f49526614da8fe97982af452e0e81
|
||||
size 9869470445
|
||||
3
pytorch_model-00007-of-00007.bin
Normal file
3
pytorch_model-00007-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4b9a3e638673e8258ea2967d5e895943023ab9f39eae34a0a95fb5e0903a9174
|
||||
size 6254090629
|
||||
610
pytorch_model.bin.index.json
Normal file
610
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,610 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 65535909888
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.40.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.45.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.46.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.50.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.54.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.54.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.54.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.55.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.norm.weight": "pytorch_model-00007-of-00007.bin"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
111556
tokenizer.json
Normal file
111556
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2d967e855b1213a439df6c8ce2791f869c84b4f3b6cfacf22b86440b8192a2f8
|
||||
size 757972
|
||||
33
tokenizer_config.json
Normal file
33
tokenizer_config.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user