Haohao-end / unsloth-fine-tuning-framework-with-LoRA-and-CoT-Q-A-data-set-wandb-visual-training-logsLinks

让AI成为你的「数字听诊器」!本项目带你在医疗推理领域玩转大模型微调,全程高能⚡- 🚀 闪电训练:基于Unsloth框架,提速2倍显存节省80%! - 🧠 医学思维链:引入CoT推理让诊断过程「透明化」 - 💊 专业领域适配:专治模型「医学知识贫血症」 - 📊 训练可视化:wandb实时监控训练过程,效果看得见 - 🎯 精准微调:LoRA技术实现「外科手术式」参数调整
47Updated 3 months ago

Alternatives and similar repositories for unsloth-fine-tuning-framework-with-LoRA-and-CoT-Q-A-data-set-wandb-visual-training-logs

Users that are interested in unsloth-fine-tuning-framework-with-LoRA-and-CoT-Q-A-data-set-wandb-visual-training-logs are comparing it to the libraries listed below

Sorting: