commit
16d095db02
1 changed files with 2 additions and 0 deletions
@ -0,0 +1,2 @@ |
|||
<br>DeepSeek open-sourced DeepSeek-R1, an LLM fine-tuned with reinforcement knowing (RL) to improve reasoning capability. DeepSeek-R1 attains results on par with OpenAI's o1 design on several standards, consisting of MATH-500 and [SWE-bench](https://coolroomchannel.com).<br> |
|||
<br>DeepSeek-R1 is based on DeepSeek-V3, [wiki.asexuality.org](https://wiki.asexuality.org/w/index.php?title=User_talk:BrandonSilvis23) a of experts (MoE) model just recently open-sourced by [DeepSeek](https://feniciaett.com). This [base design](http://63.141.251.154) is fine-tuned utilizing Group [Relative Policy](https://git.kraft-werk.si) Optimization (GRPO), a reasoning-oriented variation of RL. The research study group also [performed knowledge](https://www.suntool.top) distillation from DeepSeek-R1 to open-source Qwen and Llama designs and launched several versions of each |
Loading…
Reference in new issue