finsight / training

Commit History

Add before/after eval: serve LoRA adapter + base vs finetune comparison
36ac7d4

Maggei Claude Opus 4.8 commited on

Disable periodic eval during training
afcbe6b

Maggei Claude Opus 4.8 commited on

Make training resumable + tune for RTX4090 24G spot instance
0a7cd16

Maggei Claude Opus 4.8 commited on

Add LLaMA-Factory training config for Qwen2.5-7B LoRA
15f5538

Maggei Claude Opus 4.8 commited on