Skip to content

Issues: EvolvingLMMs-Lab/open-r1-multimodal

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

23 Open 5 Closed
23 Open 5 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

How can I cite this work?
#32 opened May 9, 2025 by Sun-Haoyuan23
What changes should we make to use different VLMs like Prismatic?
#31 opened May 3, 2025 by armanakbari
We run the eval script on a server that is not connected to the Internet, but the lmms-eval library reports an error. How should I run the eval script in an offline environment?
#30 opened Mar 20, 2025 by XiaozhenQiao
How should the data format be defined when using my dataset for GRPO training?
#29 opened Mar 18, 2025 by yanbochen716
Add Support for Gemma 3
#27 opened Mar 15, 2025 by gagan3012
1
Is there any difference between this and the knowledge distillation of GPT-4o ?
#26 opened Mar 4, 2025 by ningkp
1
Proposal to Evaluate on the HumanEval-V Benchmark for Enhanced Visual Reasoning and Code Generation
#25 opened Feb 25, 2025 by zfj1998
The guess reason of the poor training performance
#24 opened Feb 23, 2025 by zhoujiawei3
1
Maybe a bug in grpo_trainer.py
#22 opened Feb 22, 2025 by Hui-design
No clip to loss within Qwen2VLGRPOTrainer
#21 opened Feb 21, 2025 by Vincex0
Some NCCL operations have failed or timed out.
#20 opened Feb 20, 2025 by qiangtang2017
2
TypeError: can only concatenate str (not "list") to str
#19 opened Feb 17, 2025 by Felixvillas
3
Aria with GRPO
#18 opened Feb 17, 2025 by LiJunnan1992
Total Training Duration for QWEN2B/7B
#17 opened Feb 15, 2025 by say-with-you
Missing vllm Integration for Accelerated Inference in This Repository
#12 opened Feb 7, 2025 by zhaochen0110
1
Issue on reward calculation
#11 opened Feb 7, 2025 by Luodian
1
Generations after few training steps
#10 opened Feb 6, 2025 by iraj465
1
multimodal-open-r1-8k-verified dataset problem
#9 opened Feb 6, 2025 by Kindpire
Error when enabling gradient checkpointing
#8 opened Feb 6, 2025 by lololololoki
5
ncclInternalError
#7 opened Feb 4, 2025 by johnson111788
Error installing with lighteval
#5 opened Feb 3, 2025 by egmaminta
1
CUDA OOM?
#4 opened Feb 2, 2025 by FanqingM
6
Support GRPO for qwen2.5-VL?
#3 opened Jan 31, 2025 by FXLYZ
2
ProTip! Follow long discussions with comments:>50.