benjaminmabe55/flixsterz
1
0
Code Issues Projects Wiki

Add 'DeepSeek Open-Sources DeepSeek-R1 LLM with Performance Comparable To OpenAI's O1 Model'

Benjamin Mabe 2025-02-22 09:08:13 +00:00
commit d46851f467
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md Normal file

@ -0,0 +1,2 @@
<br>DeepSeek open-sourced DeepSeek-R1, an LLM fine-tuned with [reinforcement learning](http://investicos.com) (RL) to improve reasoning ability. DeepSeek-R1 [attains](https://jobs.ofblackpool.com) results on par with [OpenAI's](http://web.joang.com8088) o1 model on numerous benchmarks, consisting of MATH-500 and [archmageriseswiki.com](http://archmageriseswiki.com/index.php/User:RosieG65174) SWE-bench.<br>
<br>DeepSeek-R1 is based on DeepSeek-V3, a mixture of experts (MoE) design recently open-sourced by DeepSeek. This base design is fine-tuned utilizing Group Relative Policy [Optimization](https://lovn1world.com) (GRPO), a [reasoning-oriented variant](https://familytrip.kr) of RL. The research study group also [performed knowledge](https://gitea.taimedimg.com) distillation from DeepSeek-R1 to [open-source Qwen](https://git.cnpmf.embrapa.br) and [Llama models](http://git.zhiweisz.cn3000) and launched a number of variations of each