Skip to content

sharegpt_gpt4的看了数据跟医疗没有关系,为什么也可以用于医疗多轮对话的微调呢? #415

@cqray1990

Description

@cqray1990

Describe the Question

Please provide a clear and concise description of what the question is.

1.在10万条多语言ShareGPT GPT4多轮对话数据集shibing624/sharegpt_gpt4上SFT微调了一版baichuan-13b-chat多轮问答模型,日常问答和医疗问答效果有提升,发布微调后的LoRA权重

2.在240万条中英文医疗数据集shibing624/medical上SFT微调了一版Ziya-LLaMA-13B模型,医疗问答效果有提升,发布微调后的完整模型权重(单轮对话)
这个微调是240w的数据全部用了,还是只用了1000,看sft命令max_train_samples设置的是1000

Metadata

Metadata

Assignees

No one assigned

    Labels

    questionFurther information is requested

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions