commit
157800abfe
1 changed files with 2 additions and 0 deletions
@ -0,0 +1,2 @@ |
|||||
|
<br>[DeepSeek open-sourced](https://insta.kptain.com) DeepSeek-R1, an LLM [fine-tuned](https://truejob.co) with reinforcement learning (RL) to improve thinking capability. DeepSeek-R1 attains results on par with [OpenAI's](https://git.touhou.dev) o1 model on several standards, including MATH-500 and [SWE-bench](https://www.genbecle.com).<br> |
||||
|
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mixture of experts (MoE) design recently open-sourced by DeepSeek. This base design is [fine-tuned utilizing](https://git.sitenevis.com) Group Relative [Policy Optimization](https://careers.mycareconcierge.com) (GRPO), a [reasoning-oriented](https://git.devinmajor.com) version of RL. The research group also carried out knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama designs and [released](http://1.94.27.2333000) numerous variations of each |
Loading…
Reference in new issue