hiyouga LLaMA-Factory Discussions
Pinned Discussions
Discussions
-
You must be logged in to vote -
You must be logged in to vote -
You must be logged in to vote -
You must be logged in to vote -
You must be logged in to vote 怎么在本地命令行与导出的微调好的qwen2-2b-instruct模型进行多轮连贯视觉对话，给它图片，然后进行多轮对话
pendingThis problem is yet to be addressed -
You must be logged in to vote 你好，请问一下支持关于SQL数据集微调吗？如果支持能给一个dataset_info.json的配置样例吗？感谢！！！
pendingThis problem is yet to be addressed -
You must be logged in to vote 增量预训练的数据token量比较大，长度分布不均怎么办？
pendingThis problem is yet to be addressed -
You must be logged in to vote 目前训练日志中，训练性能指标如何分析呢？
pendingThis problem is yet to be addressed -
You must be logged in to vote qwen2.5-coder-33B 相比 qwen2.5-33B-instruct 训练需要消耗更多的显存么？
wontfixThis will not be worked on -
You must be logged in to vote -
You must be logged in to vote -
You must be logged in to vote -
You must be logged in to vote what are the minimum no. of A100sxm 80GB GPU required for lora sft finetuning of "Qwen2-VL-72B-instruct"?
solvedThis problem has been already solved -
You must be logged in to vote 如果我想实现使用http模式调用微调我应该如何实现
pendingThis problem is yet to be addressed -
You must be logged in to vote STF后发现模型的基础能力丢失
pendingThis problem is yet to be addressed -
You must be logged in to vote -
You must be logged in to vote -
You must be logged in to vote How can i set lora alpha value ?
solvedThis problem has been already solved -
You must be logged in to vote Full-Finetune worse than Lora-Finetune 全量fientuee效果差于lora
pendingThis problem is yet to be addressed -
You must be logged in to vote -
You must be logged in to vote -
You must be logged in to vote -
You must be logged in to vote 二次预训练阶段全参微调,损失曲线是否正常，如何优化
pendingThis problem is yet to be addressed -
You must be logged in to vote lora finutune QWen2.5 0.5B use CPU lora微调QWen2.5 0.5B训练使用了cpu，怎么修改为使用cuda
wontfixThis will not be worked on -
You must be logged in to vote
