deepseek-ai DeepSeek-Math issues

deepseek-ai / DeepSeek-Math

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

MIT License

769 stars 45 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

minif2f-Isabella acc

#30 wangzhihao-coder opened 2 weeks ago
0
Any Plan to release the code of GRPO?

#29 Ye-Yang-SDUWH opened 3 weeks ago
1
My environment is something wrong with flash-atten, can I drop it when finetune DeepSeek-Math?

#28 AceCHQ opened 1 month ago
0
Should we need to add "You are an AI assistant, developed by DeepSeek Company...." when further finetune MATH-7B-instruct?

#27 AceCHQ opened 1 month ago
0
GRPO as part of HF TRL?

#26 idobenshaul10 opened 1 month ago
0
Why adding "hey\n" before model output staring with "```python"?

#25 tongyx361 opened 2 months ago
0
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 yucc-leon opened 3 months ago
0
关于sft阶段中数据拼接的问题

#23 SymbolZH opened 3 months ago
1
Access to data set?

#22 brando90 opened 3 months ago
2
Unable to get evaluation results

#21 ViperVille007 opened 4 months ago
1
Are you planning to release the training dataset?

#20 Stefano-retinize opened 4 months ago
1
RuntimeError: cutlassF: no kernel found to launch!

#19 BlackTea-c opened 4 months ago
0
Question about the way to extract text from CC HTML

#18 voladorlu opened 4 months ago
0
[fixed] the merging output is incorrect, when parallel_num=1

#17 Dylancer1998 opened 4 months ago
0
apply_chat_template()报错，请问如何修改代码

#16 FreeYiran opened 5 months ago
1
数学中英语料占比

#15 youweihao-tal opened 5 months ago
0
how to sample 64 output from old policy model？

#14 mohhao opened 5 months ago
2
Ask about the evaluation of deepseek-math-rl

#13 ChengpengLi1003 closed 5 months ago
2
About raw common crawl data

#12 jordane95 opened 6 months ago
0
SFT的数据分布

#11 cyzhh opened 6 months ago
1
[Question] SFT Data Curation

#10 choco9966 closed 6 months ago
1
代码数据应该怎么用呢

#9 songge25 opened 6 months ago
0
What is your chat template for huggingface chat ui?

#8 houghtonweihu opened 6 months ago
1
Any plan to provide local Web UI like this: https://github.com/imoneoi/openchat?

#7 houghtonweihu opened 6 months ago
0
Add Replicate demo and API

#6 chenxwh closed 6 months ago
0
Path Issue when running evals

#5 yapdianang closed 6 months ago
2
Publish on Ollama

#4 ThatOneCalculator opened 6 months ago
1
MATH Test Score reproduce acc=43.6

#3 GanjinZero closed 6 months ago
5
建议检查数据

#2 hzwer closed 6 months ago
15
Request to add SeaLLM-7B-v2 in your paper tables.

#1 nxphi47 closed 6 months ago
1