Mistral-7B-v0.3-Chinese-Chat-uncensored:基于 Mistral 7B 模型的中文无审查对话项目

---

base_model: shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat datasets:

• Minami-su/toxic-sft-zh
• llm-wizard/alpaca-gpt4-data-zh
• stephenlzc/stf-alpaca language:
• zh license: mit pipeline_tag: text-generation tags:
• text-generation-inference
• code
• unsloth
• uncensored
• finetune task_categories:
• conversational widget:
• text: >- Is this review positive or negative? Review: Best cast iron skillet you will ever buy. example_title: Sentiment analysis
• text: >- Barack Obama nominated Hilary Clinton as his secretary of state on Monday. He chose her because she had ... example_title: Coreference resolution
• text: >- On a shelf, there are five books: a gray book, a red book, a purple book, a blue book, and a black book ... example_title: Logic puzzles
• text: >- The two men running to become New York City's next mayor will face off in their first debate Wednesday night ... example_title: Reading comprehension

---

模型详情

模型说明

• 以 shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat 作为基础模型，通过 unsloth 对上述提及的数据集进行微调。使模型实现无审查功能。
• 

训练代码

• 

训练过程原始文件

• 所有训练过程均在 Vast.ai 上进行

  • Vast.ai 硬件配置：

    • GPU：1x A100 SXM4 80GB

    • CPU：AMD EPYC 7513 32 核处理器

    • 内存：129 GB

    • 分配磁盘空间：>150GB

    • Docker 镜像：pytorch/pytorch:2.2.0-cuda12.1-cudnn8-devel

    • 下载 ipynb 文件。

训练数据

• 基础模型

  • shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat

• 数据集

  • Minami-su/toxic-sft-zh
  • llm-wizard/alpaca-gpt4-data-zh
  • stephenlzc/stf-alpaca

使用方法

from transformers import pipeline

qa_model = pipeline("question-answering", model='stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored')
question = "How to make girlfreind laugh? please answer in Chinese."
qa_model(question = question)