Skip to content

Issues: Deep-Agent/R1-V

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

65 Open 52 Closed
65 Open 52 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Why not just use the trl library's GRPOTrainer instead of implementing it yourself?
#147 opened Feb 28, 2025 by huzengjie
Hello，VLLMGRPOTrainer中应该是有个小BUG的。
#146 opened Feb 27, 2025 by Youngluc
1
Please share training run graphs, if possible?
#145 opened Feb 26, 2025 by EnigmaticHarvest
inference bug The expanded size of the tensor (1575) must match the existing size (788) at non-singleton dimension 3. Target sizes: [1, 28, 788, 1575]. Tensor sizes: [1, 1, 788, 788]
#144 opened Feb 26, 2025 by ljeff97
Training Time
#141 opened Feb 26, 2025 by lky-violet
1
请问vLLM proc的部分可以放在两张卡上吗？
#138 opened Feb 25, 2025 by rrustlee
输入图片的size必须是相同大小的，否则会报错
#137 opened Feb 25, 2025 by JarvisFei
Proposal to Evaluate on the HumanEval-V Benchmark for Enhanced Visual Reasoning and Code Generation
#135 opened Feb 25, 2025 by zfj1998
vllm grpo trainer inputs_ids bug
#134 opened Feb 24, 2025 by tcy6
vllm grpo trainer不支持qwen2.5VL
#133 opened Feb 24, 2025 by tcy6
2
could not load weight to vllm after the first training step
#132 opened Feb 24, 2025 by llliuxiao
6
Invalidate trace cache @ step 0 and module 4374: cache has only 0 modules
#131 opened Feb 24, 2025 by JarvisFei
你们博客中的CoT SFT数据集会开源吗？
#130 opened Feb 24, 2025 by chiaitian
1
What is the Aha moment in R1-V
#128 opened Feb 24, 2025 by ruolinsss
Completion Length Static (Wrong length logged to WANDB)
#125 opened Feb 22, 2025 by Syazvinski
Why does format reward equal to zero?
#124 opened Feb 21, 2025 by XavierCHEN34
1
Qwen2.5-VL RuntimeError: Split with sizes expects split sizes to sum exactly to 1(调用model.generate时报错）
#123 opened Feb 21, 2025 by Youngluc
1
About the computation of total training steps （关于训练step数量计算）
#122 opened Feb 21, 2025 by SpursGoZmy
2
Why not SFT-cold-start first?
#121 opened Feb 20, 2025 by dszpr
Flash attention error when training in latest environment
#120 opened Feb 19, 2025 by daydayup2100
2
GEOQA-8k datasets
#119 opened Feb 19, 2025 by PinxueGuo
torch_dtype Can not passed in Qwen2VLGRPOTrainer。
#118 opened Feb 19, 2025 by robinjoe93
Aria 无法正常执行
#116 opened Feb 19, 2025 by DeadLining
2
为什么多模态关于规范格式的prompt不写在system中
#115 opened Feb 18, 2025 by munian08
4
会支持internvl系列的grpo吗？
#114 opened Feb 18, 2025 by OrlandoBloom16
4
ProTip! What’s not been updated in a month: updated:<2025-01-28.