---
license: apache-2.0
datasets:
- Minami-su/roleplay_multiturn_chat_1k_zh_v0.1
tags:
- roleplay
- qwen
- self_instruct
---
---
language:
- zh
tags:
- roleplay
- multiturn_chat
---
## 介绍

基于self-instruct生成的多轮对话roleplay数据在qwen 7b chat上训练的模型，约1k条不同的人格数据和对话和约3k alpaca指令

## 存在问题：
1.roleplay数据基于模型自身生成，所以roleplay存在模型本身价值观融入情况，导致roleplay不够真实，不够准确。
## 使用方法：
可以参考https://github.com/PanQiWei/AutoGPTQ
## prompt：
```ipython
>>> tokenizer = AutoTokenizer.from_pretrained(ckpt,trust_remote_code=True)
>>> from auto_gptq import AutoGPTQForCausalLM
>>> model = AutoGPTQForCausalLM.from_quantized(ckpt, device_map="auto",trust_remote_code=True, use_safetensors=True).half()
>>> def generate(prompt):
>>>     print("1",prompt,"2")
>>>     input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)
>>>     generate_ids = model.generate(input_ids=input_ids,
>>>     max_length=4096,
>>>     num_beams=1,
>>>     do_sample=True, top_p=0.9, temperature=0.95, repetition_penalty=1.05, eos_token_id=tokenizer.eos_token_id)
>>>     output = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
>>>     response = output[len(prompt):]
>>>     return response
>>> device = torch.device('cuda')
>>> history=[]
>>> max_history_len=12
>>> rating="0"
>>> while True:
>>>     text=input("user:")
>>>     text=f"人类:{text}</s>"
>>>     history.append(text)
>>>     input_text="爱丽丝的人格:你叫爱丽丝，是一个傲娇，腹黑的16岁少女<|im_end|>"
>>>     for history_id, history_utr in enumerate(history[-max_history_len:]):
>>>         input_text = input_text + history_utr + '\n'
>>>     prompt = input_text+"爱丽丝:"
>>>     prompt =prompt.strip()
>>>     response = generate(prompt)
>>>     response=response.strip()
>>>     response="爱丽丝:"+response+"<|im_end|>"
>>>     print("1",response,"2")
>>>     history.append(response)
人类:我还要去上班
爱丽丝:哎呀呀~这么无聊，竟然还要去工作？
```
## 引用
```
@misc{selfinstruct,
  title={Self-Instruct: Aligning Language Model with Self Generated Instructions},
  author={Wang, Yizhong and Kordi, Yeganeh and Mishra, Swaroop and Liu, Alisa and Smith, Noah A. and Khashabi, Daniel and Hajishirzi, Hannaneh},
  journal={arXiv preprint arXiv:2212.10560},
  year={2022}
}
```