Skip to content

Issues: deepseek-ai/DeepSeek-Math

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

30 Open 6 Closed
30 Open 6 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

DPO的梯度系数推导不够严格？
#38 opened Feb 25, 2025 by liyy96
论文里PPO的公式写错了
#37 opened Feb 14, 2025 by itmorn
想入职你们公司，当个跑腿的都行
#36 opened Feb 14, 2025 by 15565763673
D
#35 opened Feb 1, 2025 by KholmogorovEA
Mathai
#34 opened Jan 29, 2025 by jerd64
数学数据筛选打分的fasttext模型能开源吗？
#33 opened Jan 24, 2025 by enddlesswm
هل تكتب عربي
#32 opened Jan 14, 2025 by SaeedDahy
Official fine-tuning code
#31 opened Oct 31, 2024 by beichenzbc
minif2f-Isabella acc
#30 opened Aug 12, 2024 by wangzhihao-coder
1
Any Plan to release the code of GRPO?
#29 opened Aug 6, 2024 by Viper403
5
My environment is something wrong with flash-atten, can I drop it when finetune DeepSeek-Math?
#28 opened Aug 1, 2024 by AceCHQ
Should we need to add "You are an AI assistant, developed by DeepSeek Company...." when further finetune MATH-7B-instruct?
#27 opened Aug 1, 2024 by AceCHQ
GRPO as part of HF TRL?
#26 opened Jul 10, 2024 by idobenshaul10
Why adding "hey\n" before model output staring with "```python"?
#25 opened Jun 15, 2024 by tongyx361
Paper 第二节预训练 2.2 节：为什么对不同 size 的数据集都要训练至高达 150B tokens？
#24 opened May 28, 2024 by yucc-leon
关于sft阶段中数据拼接的问题
#23 opened May 12, 2024 by SymbolZH
1
Access to data set?
#22 opened May 5, 2024 by brando90
2
Unable to get evaluation results
#21 opened Apr 25, 2024 by ViperVille007
1
Are you planning to release the training dataset?
#20 opened Apr 19, 2024 by Stefano-retinize
1
RuntimeError: cutlassF: no kernel found to launch!
#19 opened Apr 16, 2024 by BlackTea-c
Question about the way to extract text from CC HTML
#18 opened Apr 16, 2024 by voladorlu
apply_chat_template()报错，请问如何修改代码
#16 opened Apr 3, 2024 by FreeYiran
1
数学中英语料占比
#15 opened Mar 27, 2024 by youweihao-tal
how to sample 64 output from old policy model？
#14 opened Mar 25, 2024 by mohhao
2
About raw common crawl data
#12 opened Feb 29, 2024 by jordane95
ProTip! Updated in the last three days: updated:>2025-02-22.