commit
45b3300832
1 changed files with 2 additions and 0 deletions
@ -0,0 +1,2 @@ |
|||||
|
<br>[DeepSeek open-sourced](https://gryzor.info) DeepSeek-R1, an LLM fine-tuned with support knowing (RL) to improve thinking capability. DeepSeek-R1 attains outcomes on par with OpenAI's o1 design on a number of criteria, including MATH-500 and [SWE-bench](https://www.jobplanner.eu).<br> |
||||
|
<br>DeepSeek-R1 is based on DeepSeek-V3, a mix of specialists (MoE) model just recently open-sourced by [DeepSeek](http://media.clear2work.com.au). This base model is fine-tuned utilizing Group Relative Policy Optimization (GRPO), a reasoning-oriented variation of RL. The research team likewise performed knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama designs and [yewiki.org](https://www.yewiki.org/User:AngelFox0210) released several versions of each |
Loading…
Reference in new issue