commit
fe1d6f01f9
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 learning (RL) to improve thinking ability. DeepSeek-R1 attains results on par with OpenAI's o1 model on a number of criteria, consisting of MATH-500 and [yewiki.org](https://www.yewiki.org/User:MonaEmr133) SWE-bench.<br> |
|||
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mix of experts (MoE) model recently open-sourced by DeepSeek. This base design is fine-tuned utilizing Group Relative [Policy Optimization](https://git.tx.pl) (GRPO), a [reasoning-oriented variation](https://busanmkt.com) of RL. The research group likewise performed knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama designs and launched several versions of each |
Loading…
Reference in new issue