commit
d9f926b1b2
1 changed files with 2 additions and 0 deletions
@ -0,0 +1,2 @@ |
|||
<br>DeepSeek open-sourced DeepSeek-R1, an LLM [fine-tuned](https://iuridictum.pecina.cz) with support knowing (RL) to improve reasoning ability. DeepSeek-R1 attains outcomes on par with OpenAI's o1 design on a number of standards, consisting of MATH-500 and SWE-bench.<br> |
|||
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mix of professionals (MoE) model just recently open-sourced by DeepSeek. This [base model](http://47.244.181.255) is fine-tuned utilizing Group Relative Policy [Optimization](https://git.xaviermaso.com) (GRPO), a reasoning-oriented version of RL. The research study group also performed knowledge distillation from DeepSeek-R1 to [open-source Qwen](https://mediawiki.hcah.in) and Llama designs and launched a number of variations of each |
Loading…
Reference in new issue