commit
7f274becd8
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](https://dinle.online) (RL) to enhance reasoning [capability](http://39.108.93.0). DeepSeek-R1 attains results on par with OpenAI's o1 model on [numerous](http://gitlab.rainh.top) standards, including MATH-500 and SWE-bench.<br> |
||||
|
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mixture of professionals (MoE) design just recently open-sourced by DeepSeek. This [base design](https://39.105.45.141) is fine-tuned using Group [Relative Policy](http://www.homeserver.org.cn3000) [Optimization](https://git.augustogunsch.com) (GRPO), a [reasoning-oriented variation](https://git.coalitionofinvisiblecolleges.org) of RL. The research group likewise performed understanding distillation from DeepSeek-R1 to [open-source Qwen](http://47.103.91.16050903) and Llama models and released a number of variations of each |
Loading…
Reference in new issue