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

master
Otilia Palmerston 9 months ago
commit
192245eb29
  1. 2
      DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md

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

@ -0,0 +1,2 @@
<br>[DeepSeek open-sourced](https://gitlab.digineers.nl) DeepSeek-R1, an [LLM fine-tuned](https://legatobooks.com) with [reinforcement learning](https://links.gtanet.com.br) (RL) to [enhance thinking](http://thinkwithbookmap.com) ability. DeepSeek-R1 attains results on par with OpenAI's o1 design on several benchmarks, consisting of MATH-500 and [SWE-bench](http://154.9.255.1983000).<br>
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mix of professionals (MoE) model just recently open-sourced by [DeepSeek](http://repo.fusi24.com3000). This base design is fine-tuned using Group Relative Policy Optimization (GRPO), a reasoning-oriented variation of RL. The research group likewise [carried](https://2flab.com) out knowledge distillation from DeepSeek-R1 to open-source Qwen and [higgledy-piggledy.xyz](https://higgledy-piggledy.xyz/index.php/User:MistyGoodenough) Llama designs and [launched](https://vibestream.tv) numerous versions of each
Loading…
Cancel
Save