|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- silk-road/ChatHaruhi-Expand-118K |
|
- silk-road/ChatHaruhi_NovelWriting |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
本脚本是对千问7B模型的微调和测试，使得Qwen 7B能够有角色扮演的能力 |
|
|
|
This script fine-tunes and tests the Qwen 7B model to give Qwen 7B the capability of role playing. |
|
|
|
项目链接 https://github.com/LC1332/Chat-Haruhi-Suzumiya |
|
|
|
- 118K训练数据由[李鲁鲁](https://github.com/LC1332)收集， |
|
|
|
- 模型是由[豆角](https://github.com/goodnessSZW)训练的 |
|
|
|
- Qwen inference代码由[米唯实](https://github.com/hhhwmws0117)编写，并接入Chatharuhi，目前进行本模型维护和bug解决 |
|
|
|
- 李鲁鲁编写了ChatHaruhi内部的prompt组织函数 |
|
|
|
|
|
A Harry Potter test see in https://github.com/LC1332/Chat-Haruhi-Suzumiya/blob/main/notebook/Harry_Potter_test_on_Qwen7B.ipynb |
|
|
|
使用方法 |
|
|
|
载入函数 |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModel, AutoModelForCausalLM |
|
tokenizer = AutoTokenizer.from_pretrained("silk-road/ChatHaruhi_RolePlaying_qwen_7b", trust_remote_code=True) |
|
model = AutoModelForCausalLM.from_pretrained("silk-road/ChatHaruhi_RolePlaying_qwen_7b", device_map="auto", trust_remote_code=True) |
|
model = model.eval() |
|
``` |
|
|
|
具体看https://github.com/LC1332/Chat-Haruhi-Suzumiya/blob/main/notebook/ChatHaruhi_x_Qwen7B.ipynb 这个notebook |
|
|
|
```python |
|
from ChatHaruhi import ChatHaruhi |
|
|
|
chatbot = ChatHaruhi( role_name = 'haruhi', max_len_story = 1000 ) |
|
|
|
prompt = chatbot.generate_prompt(role='阿虚', text = '我看新一年的棒球比赛要开始了！我们要去参加吗？') |
|
|
|
response, history = model.chat(tokenizer, prompt, history=[]) |
|
print(response) |
|
|
|
chatbot.append_response(response) |
|
``` |
|
|
|
目前支持 |
|
role_name |
|
|
|
role_from_hf |
|
|
|
role_from_jsonl |
|
|
|
多种角色格式载入。 |
|
|
|
|
