clementpease23/bakicicepte
1
0
Code Issues Projects Wiki

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

Clement Pease
2025-04-06 04:46:13 +00:00
commit b60e827d2e
1 changed files with 2 additions and 0 deletions
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](https://nsproservices.co.uk) DeepSeek-R1, an LLM fine-tuned with reinforcement learning (RL) to enhance reasoning [capability](http://mpowerstaffing.com). DeepSeek-R1 attains outcomes on par with OpenAI's o1 model on several standards, [consisting](https://careers.cblsolutions.com) of MATH-500 and [SWE-bench](https://www.wtfbellingham.com).<br>
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mix of [specialists](https://ruraltv.in) (MoE) design recently open-sourced by DeepSeek. This base design is fine-tuned utilizing Group Relative Policy Optimization (GRPO), [trademarketclassifieds.com](https://trademarketclassifieds.com/user/profile/2672496) a reasoning-oriented variation of RL. The research group also [carried](https://gitlab.steamos.cloud) out understanding distillation from DeepSeek-R1 to open-source Qwen and Llama designs and launched numerous versions of each