-
Notifications
You must be signed in to change notification settings - Fork 113
Issues: openreasoner/openr
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
LM generation with strange behavior
bug
Something isn't working
#93
opened Jan 3, 2025 by
hyuenmin-choi
2 of 4 tasks
The current WeChat QR code appears to be invalid. Kindly provide an updated version for further communication.
bug
Something isn't working
#92
opened Dec 25, 2024 by
baifanxxx
4 tasks
prm训练代码用到的测试集../../datasets/prm800k_test.json麻烦提供一下,谢谢
enhancement
New feature or request
#91
opened Dec 19, 2024 by
zhangyanbo2007
Adding Diverse Verifier Tree Search (DVTS)
enhancement
New feature or request
#88
opened Dec 16, 2024 by
ShayekhBinIslam
Executing bash train_1lm.sh resulted in an IndexError error: index -1 is out of bounds for dimension 0 with size 0
bug
Something isn't working
#86
opened Dec 15, 2024 by
tju-hwh
4 tasks
Process hangs when using the given metrics to evaluate in PRM multi-gpu training.
bug
Something isn't working
#83
opened Dec 9, 2024 by
great-luao
2 of 4 tasks
Is there a bug in rStar's A2 operation
bug
Something isn't working
#81
opened Dec 9, 2024 by
windks
4 tasks
train_math.py model file save error
bug
Something isn't working
#78
opened Dec 6, 2024 by
Tshiyao
2 of 4 tasks
RL training , Critic MCTS : supported already ? or on the roadmap ?
enhancement
New feature or request
#73
opened Dec 6, 2024 by
BerenLuthien
Pad token issue with MATH-psa and Qwen2.5-math-7B ins
bug
Something isn't working
#71
opened Dec 4, 2024 by
LUMO666
2 of 4 tasks
IndexError: index 621236954739970 is out of bounds for dimension 0 with size 151936
while running sh scripts/eval/cot_greedy.sh
bug
#66
opened Nov 29, 2024 by
Lolo1222
2 of 4 tasks
Error in reproducing train_math.py: input_ids里没有step_tag_id
bug
Something isn't working
#64
opened Nov 26, 2024 by
zeroxleo
2 of 4 tasks
Question about the model size
bug
Something isn't working
#63
opened Nov 26, 2024 by
yitianlian
2 of 4 tasks
7B模型RL训练需要多少显存
question
Further information is requested
#60
opened Nov 21, 2024 by
linyaoyang
2 of 4 tasks
Will this project support prm training of soft label?
enhancement
New feature or request
#57
opened Nov 13, 2024 by
Dada-Cloudzxy
Json decoding failed. A bug with about a 20% chance of occurring.
bug
Something isn't working
#50
opened Nov 9, 2024 by
Dada-Cloudzxy
2 of 4 tasks
Possible Out of Index bug when reasoning with Qwen
bug
Something isn't working
#48
opened Nov 9, 2024 by
Dada-Cloudzxy
2 of 4 tasks
Where the finetuned prm , (eg qwen, or llama), is leveraged?
enhancement
New feature or request
#45
opened Nov 6, 2024 by
mustardBloom
Previous Next
ProTip!
Updated in the last three days: updated:>2025-01-03.