nestorfoskett/122
1
0
Code Issues Projects Wiki

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

Nestor Foskett 2025-02-21 21:56:47 -06:00
commit 0d78e81cb0
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 support knowing (RL) to enhance thinking capability. DeepSeek-R1 attains results on par with OpenAI's o1 design on numerous benchmarks, including MATH-500 and SWE-bench.<br>
<br>DeepSeek-R1 is based on DeepSeek-V3, a [mixture](https://git.laser.di.unimi.it) of experts (MoE) model just recently open-sourced by DeepSeek. This base design is fine-tuned utilizing Group Relative Policy Optimization (GRPO), a [reasoning-oriented](http://140.143.208.1273000) version of RL. The research [study team](https://gogs.sxdirectpurchase.com) likewise performed understanding [distillation](http://42.192.14.1353000) from DeepSeek-R1 to [open-source Qwen](https://satitmattayom.nrru.ac.th) and Llama models and launched a number of [versions](https://district-jobs.com) of each