hiyouga LLaMA-Factory Q-a Discussions
Pinned Discussions
Q&A Discussions
Ask the community for help
-
You must be logged in to vote 对qwen2基模进行dpo训练效果差
wontfixThis will not be worked on -
You must be logged in to vote 预测结果 评估 指标
pendingThis problem is yet to be addressed -
You must be logged in to vote -
You must be logged in to vote 多个lora接续训练求助！
pendingThis problem is yet to be addressed -
You must be logged in to vote Llama pro训练后的模型加数据训练
pendingThis problem is yet to be addressed -
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 -
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 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 react问题，重新描述
pendingThis problem is yet to be addressed -
You must be logged in to vote 微调后原始模型没有react功能
solvedThis problem has been already solved -
You must be logged in to vote -
You must be logged in to vote 如何画不同数据的损失？
pendingThis problem is yet to be addressed -
You must be logged in to vote 500条数据训练完全无效果
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 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
