commit
5c7b419d21
1 changed files with 2 additions and 0 deletions
@ -0,0 +1,2 @@ |
|||
<br>[DeepSeek open-sourced](https://whotube.great-site.net) DeepSeek-R1, an LLM fine-tuned with reinforcement learning (RL) to improve thinking ability. DeepSeek-R1 [attains](https://www.megahiring.com) [outcomes](https://community.scriptstribe.com) on par with OpenAI's o1 model on several standards, [including](https://www.opentx.cz) MATH-500 and [SWE-bench](http://www.vokipedia.de).<br> |
|||
<br>DeepSeek-R1 is based on DeepSeek-V3, a mix of (MoE) model recently open-sourced by DeepSeek. This base design is fine-tuned utilizing Group Relative Policy Optimization (GRPO), a reasoning-oriented variation of RL. The research group also performed knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama designs and launched a number of variations of each |
Loading…
Reference in new issue