Giters
TideDra
/
VL-RLHF
A RLHF Infrastructure for Vision-Language Models
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
90
Watchers:
4
Issues:
14
Forks:
5
TideDra/VL-RLHF Issues
[BUG] Value Error noqa:E501
Updated
2 months ago
Any suggestion on how to modify code to train single textual modality
Closed
2 months ago
支持cogvlm2模型的强化学习训练吗
Updated
2 months ago
微调LLaVA报错
Updated
3 months ago
Comments count
4
微调qwen爆内存
Updated
3 months ago
Comments count
3
请问支持对internvl-1-5的微调吗?如果可以的话显存应该预留多少
Updated
3 months ago
Comments count
2
Reproduction of InternLM-XComposer2
Updated
3 months ago
Comments count
1
不使用lora报错
Updated
4 months ago
Comments count
1
微调internXC2报错
Updated
4 months ago
Comments count
9
Support for SFT InternLM-XComposer2?
Closed
4 months ago
Comments count
1
Support for InstructBlipPPOTrainer
Updated
4 months ago
strip may break chat template
Closed
6 months ago