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

master
Miguel Baumgartner 9 months ago
commit
28bdd66977
  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://pattonlabs.com) DeepSeek-R1, an [LLM fine-tuned](https://gogs.adamivarsson.com) with reinforcement knowing (RL) to improve reasoning ability. DeepSeek-R1 attains outcomes on par with [OpenAI's](https://career.logictive.solutions) o1 design on a number of criteria, consisting of MATH-500 and SWE-bench.<br>
<br>DeepSeek-R1 is based on DeepSeek-V3, a mixture of specialists (MoE) model just recently open-sourced by DeepSeek. This [base design](https://gogs.koljastrohm-games.com) is fine-tuned [utilizing](http://bingbinghome.top3001) Group Relative Policy [Optimization](https://git.riomhaire.com) (GRPO), a [reasoning-oriented](https://mxlinkin.mimeld.com) version of RL. The research team likewise carried out knowledge distillation from DeepSeek-R1 to open-source Qwen and [raovatonline.org](https://raovatonline.org/author/giagannon42/) Llama models and released a number of versions of each
Loading…
Cancel
Save