deepseekmirror/DeepSeek-R1
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-R1.git synced 2025-02-22 21:59:00 -05:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Manas Dey 2025-01-28 23:59:12 +05:30 committed by GitHub
parent 1108785f81
commit dbc3a01195
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
README.md
View File

@ -53,6 +53,13 @@ we introduce DeepSeek-R1, which incorporates cold-start data before RL.
DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks.
To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on Llama and Qwen. DeepSeek-R1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models. To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on Llama and Qwen. DeepSeek-R1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.
**Key Features**
- State-of-the-art performance in reasoning tasks
- Open-source availability of both main models
- Six dense distilled models based on Llama and Qwen architectures
- 32,768 token context length support
- Comprehensive benchmark results across multiple domains
**NOTE: Before running DeepSeek-R1 series models locally, we kindly recommend reviewing the [Usage Recommendation](#usage-recommendations) section.** **NOTE: Before running DeepSeek-R1 series models locally, we kindly recommend reviewing the [Usage Recommendation](#usage-recommendations) section.**