main

TTobi LütkeMove GRPO training out of default finetune pipeline

189916d6创建于 2月23日历史提交

文件	最后提交记录	最后更新时间
accelerate_multi_gpu.yaml	lots of training stuff	3 个月前
sft-lfm2.yaml	Merge origin/main into feat/ast-aware-chunking Resolve conflicts: combine AST chunking args (filepath, chunkStrategy) with abort signal parameter from #458. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	1 个月前
sft.yaml	Add wall-clock checkpoints and full eval defaults	2 个月前
sft_local.yaml	Add wall-clock checkpoints and full eval defaults	2 个月前