Skip to content

Issues: om-ai-lab/VLM-R1

Beta
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

124 Open 128 Closed
124 Open 128 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Issue with use_libuv = 0
#303 opened Jun 11, 2025 by travailmachine
为什么要设置max_steps
#302 opened Jun 11, 2025 by xxyliuyang
ovd data
#301 opened Jun 11, 2025 by lfreee
trl installation causes a version mismatch with transformers version 4.49.0
#300 opened Jun 10, 2025 by Darsha-1
No module named 'math_verify'
#299 opened Jun 10, 2025 by Darsha-1
OVD Demo runtime error
#297 opened Jun 10, 2025 by ccc123590
Question about cosine_reward
#296 opened Jun 9, 2025 by liuxuexun
1
Lisa test is invalid.
#295 opened Jun 8, 2025 by Qi-Zhangyang
1
During a certain step in the training process, an NCCL communication timeout was reported, but there was no error message related to any single GPU.
#294 opened Jun 8, 2025 by xiangwentao666
how the proposed RL training affects the VQA performance
#293 opened Jun 8, 2025 by twangnh
Parameters seems not being updated
#291 opened Jun 6, 2025 by hanyangclarence
Why The padding side must be set to "left" during training
#290 opened Jun 5, 2025 by lujiazho
2
Port: 29500 address already in use
#289 opened Jun 4, 2025 by hieuhthh
Question on Zero-shot Performance and Bounding Box Coordinates in Qwen-VL 2.5
#288 opened Jun 4, 2025 by LijunRio
Tensor shape not match for internvl when gradient_checkpointing is True
#287 opened Jun 4, 2025 by zyandtom
2
训练过程问题
#286 opened Jun 4, 2025 by Why0912
2
How to add negative samples?
#285 opened Jun 3, 2025 by shengyuwoo
请问有计划开源D3的训练样例吗？
#284 opened Jun 2, 2025 by tzjtatata
training cost
#283 opened Jun 2, 2025 by twangnh
我在自己数据集微调时报错：AttributeError: 'Qwen2_5_VLForConditionalGeneration' object has no attribute 'vision_model'
#282 opened Jun 1, 2025 by Wuwenji18
2
关于grpo_rec.py、grpo_jsonl.py图片处理的区别
#281 opened May 31, 2025 by JepsonWong
为什么completion_length越训越短
#280 opened May 27, 2025 by BoggySyb
2
AttributeError: 'Qwen2_5_VLModel' object has no attribute 'embed_tokens'
#279 opened May 25, 2025 by gray114514
6
How to train multi task_types
#278 opened May 24, 2025 by hieuhthh
How to make the training data follow the image sequence specified in the JSON file during training?
#277 opened May 21, 2025 by sms-s
ProTip! Type g i on any issue or pull request to go back to the issue listing page.