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

master
Bridget Carnes 3 months ago
commit
024bdbafaa
  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 DeepSeek-R1, an LLM [fine-tuned](https://healthcarejob.cz) with [support knowing](https://electroplatingjobs.in) (RL) to enhance thinking ability. DeepSeek-R1 [attains](https://twentyfiveseven.co.uk) outcomes on par with [OpenAI's](https://www.so-open.com) o1 design on several benchmarks, MATH-500 and SWE-bench.<br>
<br>DeepSeek-R1 is based on DeepSeek-V3, a mixture of experts (MoE) design recently open-sourced by DeepSeek. This base model is fine-tuned utilizing Group Relative Policy Optimization (GRPO), a reasoning-oriented variation of RL. The research team also [carried](https://1millionjobsmw.com) out understanding distillation from DeepSeek-R1 to [open-source Qwen](https://gitea.gai-co.com) and [Llama designs](https://gitlab.damage.run) and released several versions of each
|||||||
100:0
Loading…
Cancel
Save