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

3 months ago · b4ee735a51
1 changed files with 2 additions and 0 deletions
--- a/DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md
+++ b/DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md
@ -0,0 +1,2 @@
 <br>DeepSeek open-sourced DeepSeek-R1, an LLM fine-tuned with reinforcement [learning](http://aiot7.com3000) (RL) to improve thinking ability. DeepSeek-R1 [attains](https://code.smolnet.org) results on par with [OpenAI's](http://124.223.222.613000) o1 model on several benchmarks, consisting of MATH-500 and  [trademarketclassifieds.com](https://trademarketclassifieds.com/user/profile/2672496) SWE-bench.<br>
 <br>DeepSeek-R1 is based on DeepSeek-V3, a mix of [professionals](https://geetgram.com) (MoE) design just 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 team likewise [performed knowledge](http://gitlab.together.social) distillation from DeepSeek-R1 to [open-source Qwen](http://git.taokeapp.net3000) and Llama [designs](https://retailjobacademy.com) and released a number of versions of each