commit
75a7c44290
1 changed files with 2 additions and 0 deletions
@ -0,0 +1,2 @@ |
|||
<br>DeepSeek open-sourced DeepSeek-R1, [wiki.vst.hs-furtwangen.de](https://wiki.vst.hs-furtwangen.de/wiki/User:MichaelCrocker0) an LLM fine-tuned with reinforcement learning (RL) to [improve thinking](http://haiji.qnoddns.org.cn3000) [ability](https://20.112.29.181). DeepSeek-R1 attains results on par with OpenAI's o1 design on a number of benchmarks, including MATH-500 and SWE-bench.<br> |
|||
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mix of specialists (MoE) model recently open-sourced by DeepSeek. This base model is fine-tuned utilizing Group Relative Policy [Optimization](https://www.meetgr.com) (GRPO), a [reasoning-oriented variation](https://gogs.lnart.com) of RL. The research study team likewise performed [understanding distillation](http://www.chinajobbox.com) from DeepSeek-R1 to open-source Qwen and [Llama designs](http://careers.egylifts.com) and launched a number of versions of each |
Loading…
Reference in new issue