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 |
jingyaogong
|
094f88a087
|
[feat] update readme
|
2025-10-22 10:58:52 +08:00 |
gongjy
|
1fc98152c0
|
detail adjustment & formatting
|
2024-11-03 11:39:46 +08:00 |
xinyanghuang7
|
c41b22a508
|
speedup and siglip
|
2024-11-02 03:21:22 -04:00 |
|
xinyanghuang7
|
2b04fce5f6
|
multi-images training
|
2024-10-30 08:46:16 -04:00 |
|
xinyanghuang7
|
085976953c
|
multi-images training
|
2024-10-30 07:52:31 -04:00 |
|
xinyanghuang7
|
ce4736dad7
|
multi-images training
|
2024-10-30 07:42:34 -04:00 |
|
xinyanghuang7
|
2adb3d15a0
|
multi-images training
|
2024-10-30 07:40:21 -04:00 |
|
xinyanghuang7
|
502fe28f33
|
add multi-image
|
2024-10-29 10:06:02 -04:00 |
|
xinyanghuang7
|
8508089ad2
|
add multi-image
|
2024-10-29 10:06:02 -04:00 |
|
xinyanghuang7
|
e13ece7937
|
add multi-images
|
2024-10-29 05:59:01 -04:00 |
|
xinyanghuang7
|
c78bf958fa
|
add multi-images
|
2024-10-29 05:59:01 -04:00 |
|
xinyanghuang7
|
a3f489005c
|
Remove large files and update .gitignore
|
2024-10-29 05:52:19 -04:00 |
|
xinyanghuang7
|
4dd3498e72
|
Remove large files and update .gitignore
|
2024-10-29 05:52:19 -04:00 |
|
xinyanghuang7
|
d28564c215
|
add multi-images
|
2024-10-29 05:45:43 -04:00 |
|
xinyanghuang7
|
e31b584feb
|
add multi-images
|
2024-10-29 05:45:43 -04:00 |