hiyouga LLaMA-Factory Discussions
Pinned Discussions
Discussions
-
You must be logged in to vote -
You must be logged in to vote 关于Qwen2-72B 全量参数微调所需的显卡下限
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 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 选择题类型数据集如何编写dataset_info.json格式
pendingThis problem is yet to be addressed -
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 -
You must be logged in to vote 使用llama3_lora_pretrain.yaml微调模型后，模型生成能力严重丧失
pendingThis problem is yet to be addressed -
You must be logged in to vote 训练集output长度1万8，微调时cutoff_len设置为2万，效果不好怎么办？
pendingThis problem is yet to be addressed -
You must be logged in to vote -
You must be logged in to vote 0.9.0版本的label构建方式
pendingThis problem is yet to be addressed -
You must be logged in to vote -
You must be logged in to vote What is the correct meaning of the cutoff_len parameter?
pendingThis problem is yet to be addressed -
You must be logged in to vote
