Skip to content

Issues: hkust-nlp/simpleRL-reason

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

25 Open 55 Closed
25 Open 55 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

Over-Reliance on Format Rewards
#85 opened May 6, 2025 by Go4miii
plan to support NPU ？
#82 opened Apr 27, 2025 by wandouguo
1
Actor died without any reason
#80 opened Apr 16, 2025 by shuminwang-ai
1
math_verify and latex2sympy2_extended need python>=3.10,
#77 opened Apr 15, 2025 by zyf8818
3
Why does using Qwen-2.5-1.5B generate garbled text during training and produce particularly poor results?
#67 opened Apr 2, 2025 by LLMforScience
13
Question about Response Length
#65 opened Apr 1, 2025 by ayyyq
2
Question about AIME24 Evaluation
#64 opened Apr 1, 2025 by Zhuofeng-Li
1
Did you guys use a cloud provider?
#63 opened Apr 1, 2025 by aidando73
5
can I have the training config for Qwen 0.5B and 1.5B
#61 opened Apr 1, 2025 by vengdeng
12
model context length should be greater than total sequence length
#58 opened Mar 30, 2025 by Su-my
2
Evaluation Results
#52 opened Mar 27, 2025 by Wloner0809
2
Intermediate checkpoints?
#47 opened Mar 18, 2025 by sz85512678
2
Questions about evaluation results
#46 opened Mar 7, 2025 by yingyibiao
5
Eval code for the hkust-nlp/Qwen-2.5-Math-7B-SimpleRL-Zero
#45 opened Feb 28, 2025 by yifan1130
1
Is the whole MATH training set corresponds to around 7 steps?
#41 opened Feb 20, 2025 by HCHCXY
2
Use reinforce
#35 opened Feb 15, 2025 by supermancmk
2
model can not saved
#34 opened Feb 12, 2025 by glennccc
3
Will you release code without ray?
#31 opened Feb 7, 2025 by zihaoli0629
4
Does rStar-Math use RL data?
#28 opened Feb 6, 2025 by john1226966735
Have you tried to train the model by Lora? It requires less computation resources.
#21 opened Jan 31, 2025 by whpy
2
RuntimeError: Connection closed by peer when training on a single node
#17 opened Jan 29, 2025 by daxiongshu
1
Where is the long CoT data and preprocess script?
#16 opened Jan 28, 2025 by butterluo
1
Docker Container for Reproducing
#15 opened Jan 28, 2025 by Kartik14
2
rStar-Math-7B row in the first table seems to be inaccurate?
#12 opened Jan 27, 2025 by rht
Please give a repro on ray cluster setup?
#9 opened Jan 26, 2025 by kouroshHakha
7
ProTip! Exclude everything labeled bug with -label:bug.