Skip to content

Issues: deepseek-ai/DeepSeek-R1

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

181 Open 87 Closed
181 Open 87 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

Clarification on the use of --enforce-eager flag in vLLM
#339 opened Feb 8, 2025 by haowang-cqu
请问 R1 模型思考过程的数据结构未来会以哪种为准？
#338 opened Feb 8, 2025 by YumoImer
1
How to reproduce deepseek R1-671b model performance on AIME2024
#336 opened Feb 8, 2025 by xiaoycolor
How does the Deepseekr1-zero model distillation work with base models like LLaMA or Qwen?
#335 opened Feb 8, 2025 by QuantaoYao
Potential Memory Utilization Issue with vLLM Deployment of DeepSeek-R1-AWQ Model in Long Context Scenarios
#334 opened Feb 8, 2025 by le0820
ChatU第一时间集成了DeepSeek-R，欢迎企业开户体验
#333 opened Feb 8, 2025 by liudao
请问一下api什么时候可以恢复购买呢？最近即便是聊天也经常是服务器繁忙，感谢。
#331 opened Feb 8, 2025 by flashal1
1
并发数超过100的，一般采用什么工具部署呢
#330 opened Feb 8, 2025 by wxzwxz131
1
关于RAG自建知识库检索问题
#328 opened Feb 8, 2025 by 457775987
4
奇怪的无限输出bug
#326 opened Feb 8, 2025 by Jingle-Pan
VRAM required for inference
#325 opened Feb 8, 2025 by treya-lin
Where can I download the dataset and training weights of DeepSeek - R1?
#324 opened Feb 8, 2025 by lizhichao999
2
不本地部署如何实现模型微调，建立知识库，deepseek api能理解并回答知识库里的内容
#323 opened Feb 8, 2025 by zhuyongbo100
3
【寻求合作】关于deepseek公版安卓APK商用的问题
#321 opened Feb 8, 2025 by suhy07
1
请问R1训练是不是只做了论文中写的2.3.3和2.3.4的内容，而2.3.1和2.3.2实际上只是为了生成数据给2.3.3用的？
#320 opened Feb 8, 2025 by ciaoyizhen
1
DeepSeek Train pipeline Problem
#319 opened Feb 8, 2025 by SCismycat
vllm uses wrong backend
#318 opened Feb 7, 2025 by zwh20081
为什么我用transformer使用模型会有奇怪回复
#317 opened Feb 7, 2025 by panrc
4
R1:32B本地部署是否支持FIM补全功能？或者deepseek-coder模型后续是否升级到R1-coder ?
#315 opened Feb 7, 2025 by CMBnetwork
1
Problem: Unstable Response When Calling deepseek-reasoner Model (DeepSeek-R1) via API
#314 opened Feb 7, 2025 by DavidMastrenet
Why does selecting the deepseek-reasoner model using the deepseek api mostly return null?为什么使用deepseek api选取deepseek-reasoner模型大多返回空？
#313 opened Feb 7, 2025 by JiachengGU1711
联网功能怎么实现？
#312 opened Feb 7, 2025 by Dayong99
About the doubts regarding the data processing of the first phase SFT section
#311 opened Feb 7, 2025 by mlshenkai
[BUG] Receipt download failed-无法下载发票
#310 opened Feb 7, 2025 by Lilliansiyin
Why is the CoT length shorter in DeepSeek R1 API than in the chatbot?
#309 opened Feb 7, 2025 by fengyao12
ProTip! Adding no:label will show everything without a label.