1 changed files with 2 additions and 0 deletions
@ -0,0 +1,2 @@ |
|||
<br>[DeepSeek open-sourced](https://git.zyhhb.net) DeepSeek-R1, an LLM fine-tuned with support knowing (RL) to improve reasoning capability. DeepSeek-R1 attains outcomes on par with OpenAI's o1 model on a number of benchmarks, including MATH-500 and [SWE-bench](https://git.xaviermaso.com).<br> |
|||
<br>DeepSeek-R1 is based on DeepSeek-V3, a mixture of experts (MoE) design recently open-sourced by DeepSeek. This [base design](https://setiathome.berkeley.edu) is fine-tuned utilizing Group Relative Policy Optimization (GRPO), a [reasoning-oriented variation](http://120.26.64.8210880) of RL. The research study team also performed understanding distillation from DeepSeek-R1 to open-source Qwen and Llama designs and launched several [variations](https://smartcampus-seskoal.id) of each |
Loading…
Reference in new issue