Skip to content

Issues: simplescaling/s1

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

58 Open 40 Closed
58 Open 40 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

Is the code data used in the training data?
#112 opened Apr 8, 2025 by xuhu0115
4
Training time shows 18 hr on 16 * H100
#111 opened Apr 4, 2025 by kartikjain-sudo
2
Config for smaller models
#110 opened Apr 1, 2025 by DoubtedSteam
1
Why generate more than 8k tokens at a time?
#109 opened Apr 1, 2025 by JaydencoolCC
1
Issue Reproducing s1.1-32B Training Loss (Observed vs. WandB)
#108 opened Mar 31, 2025 by dzh19990407
8
Can I specify the thinking context of the query when s1 inferencing with vllm?
#107 opened Mar 24, 2025 by Siki-cloud
1
qwen2.5-32B can not fine tuning on 80GB A100 in max_seq_length=32768
#106 opened Mar 21, 2025 by Gresham429
4
why the model file size is 129g?
#104 opened Mar 20, 2025 by wikithink
1
The minimum GPU resources needed to fine-tune the 32B model?
#103 opened Mar 19, 2025 by JaydencoolCC
1
Error in Evaluating on Other Dataset (AssertionError: min_tokens_thinking only supports until_thinking tokens that are 1 token long)
#102 opened Mar 19, 2025 by jd730
3
Exploring LoRA Adapters & Low Precision Training in S1 for Enhanced Test-Time Scaling
#101 opened Mar 19, 2025 by goravaa
s1-32b keeps generating same trajectories and final answer regardless of changing of seeds
#97 opened Mar 12, 2025 by nichenshun
1
Experimental communication
#96 opened Mar 12, 2025 by WYH1597650869
1
ValueError: please provide at least one prompt
#95 opened Mar 11, 2025 by TikaToka
5
Token-conditonal control code?
#93 opened Mar 10, 2025 by kyZhao-1
1
How is the AIME24 dataset of 30 rows created ?
#92 opened Mar 9, 2025 by Stefanie-Anna
1
About Figure4 (a) and Table 1
#91 opened Mar 5, 2025 by Aegis1863
3
Question on rejection sampling and Fig 6 in paper.
#89 opened Mar 4, 2025 by lihkinVerma
1
Is OPENAI_API_KEY necessary?
#87 opened Mar 4, 2025 by kyZhao-1
3
Gemini thinking flash API no longer returns thoughts and response separately
#85 opened Mar 3, 2025 by SusMaria
1
groundtruth answer of s1 dataset
#84 opened Feb 26, 2025 by jiayuww
1
what is the reason set pad_token to unused token?
#83 opened Feb 25, 2025 by blackcherry88
4
How do we verify the generated proof?
#74 opened Feb 24, 2025 by agoyang
1
Script to generate traces via DeepSeek R1 seems to be missing
#73 opened Feb 24, 2025 by nileshtrivedi
1
Inference Token Inclusion and SFT Question Loss Calculation Queries
#72 opened Feb 23, 2025 by ruio248
1
ProTip! Updated in the last three days: updated:>2025-04-09.