minimind-v/trainer
MiniMind-V User 62f47fb844 [fix] LoRA/RAG: correct target modules, vlm_checkpoint call, and gitignore
- lora_utils.py: fix target_modules to match MiniMind arch (q/k/v/o_proj
  instead of GPT-2 style c_attn/c_proj/c_fc)
- train_sft_vlm_lora.py: fix broken vlm_checkpoint call in train_epoch
  (was passing model/epoch/step/args instead of vlm_config); now saves
  inline like train_sft_vlm.py; remove unused SkipBatchSampler import
- .gitignore: add __pycache__, .claude/, dataset/sft_vlm.parquet
2026-03-06 04:49:40 +00:00
..
lora_utils.py [fix] LoRA/RAG: correct target modules, vlm_checkpoint call, and gitignore 2026-03-06 04:49:40 +00:00
train_pretrain_vlm.py [update] dataset name 2026-02-05 00:22:58 +08:00
train_sft_vlm.py [update] dataset name 2026-02-05 00:22:58 +08:00
train_sft_vlm_lora.py [fix] LoRA/RAG: correct target modules, vlm_checkpoint call, and gitignore 2026-03-06 04:49:40 +00:00
trainer_utils.py [update] sync minimind 2026-01-15 21:51:58 +08:00