cassandratowns/emplealista
1
0
Code Issues Projects Wiki

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

Cassandra Townson
2025-04-06 23:56:08 +00:00
commit 741bdb0efb
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://asteroidsathome.net) DeepSeek-R1, an LLM fine-tuned with reinforcement knowing (RL) to enhance thinking capability. DeepSeek-R1 attains results on par with OpenAI's o1 design on a number of standards, [consisting](https://itheadhunter.vn) of MATH-500 and SWE-bench.<br>
<br>DeepSeek-R1 is based on DeepSeek-V3, a mix of professionals (MoE) design recently open-sourced by [DeepSeek](http://43.143.46.763000). This base model is fine-tuned utilizing Group Relative Policy Optimization (GRPO), a reasoning-oriented version of RL. The research study group also carried out understanding distillation from DeepSeek-R1 to open-source Qwen and Llama designs and launched a number of versions of each