Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,38 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- zh
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- llama
|
8 |
+
- llama3
|
9 |
+
---
|
10 |
+
|
11 |
+
---
|
12 |
+
frameworks:
|
13 |
+
- Pytorch
|
14 |
+
license: Apache License 2.0
|
15 |
+
tasks:
|
16 |
+
- chatbot
|
17 |
+
|
18 |
+
language:
|
19 |
+
- cn
|
20 |
+
|
21 |
+
tags:
|
22 |
+
- RL-tuned
|
23 |
+
|
24 |
+
tools:
|
25 |
+
- vllm
|
26 |
+
---
|
27 |
+
Github:https://github.com/CrazyBoyM/llama3-Chinese-chat
|
28 |
+
放出训练配方细节供网友参考分享:
|
29 |
+
DPO(beta 0.5) + lora rank128, alpha256 + 打开"lm_head", "input_layernorm", "post_attention_layernorm", "norm"层训练。
|
30 |
+
偏好中文和emoji表情,且不损伤原instruct版模型能力。
|
31 |
+
|
32 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/631f5b422225f12fc0f2c838/2xlWxZvN0gahckA2EPmlE.png)
|
33 |
+
|
34 |
+
Git下载
|
35 |
+
```
|
36 |
+
#Git模型下载
|
37 |
+
git clone https://www.modelscope.cn/baicai003/Llama3-Chinese-instruct-DPO-beta0.5.git
|
38 |
+
```
|