license: apache-2.0 datasets:

• silk-road/ChatHaruhi-Expand-118K
• silk-road/ChatHaruhi_NovelWriting pipeline_tag: text-generation

本脚本用于对千问7B模型进行微调与测试，赋予Qwen 7B角色扮演能力

项目链接 https://github.com/LC1332/Chat-Haruhi-Suzumiya

• 118K训练数据由李鲁鲁采集
• 模型训练由豆角完成
• Qwen推理代码由米唯实编写并集成至ChatHaruhi，现负责模型维护与问题修复
• ChatHaruhi核心提示词组织函数由李鲁鲁开发

哈利波特测试案例详见：https://github.com/LC1332/Chat-Haruhi-Suzumiya/blob/main/notebook/Harry_Potter_test_on_Qwen7B.ipynb

使用指南

模型加载

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()

详细示例参见：https://github.com/LC1332/Chat-Haruhi-Suzumiya/blob/main/notebook/ChatHaruhi_x_Qwen7B.ipynb

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)

当前支持角色加载方式：

• role_name
• role_from_hf
• role_from_jsonl 多种角色格式兼容