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

master
Leta Addis 1 week ago
commit
55dbc2a045
1 changed files with 2 additions and 0 deletions
  1. +2
    -0
      DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md

+ 2
- 0
DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md

@ -0,0 +1,2 @@
<br>[DeepSeek open-sourced](https://watch.bybitnw.com) DeepSeek-R1, an LLM fine-tuned with support learning (RL) to improve thinking ability. DeepSeek-R1 attains results on par with OpenAI's o1 design on numerous criteria, [consisting](https://tube.zonaindonesia.com) of MATH-500 and [SWE-bench](https://git.soy.dog).<br>
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mixture of [experts](http://git.rabbittec.com) (MoE) design recently [open-sourced](https://abcdsuppermarket.com) by DeepSeek. This base model is fine-tuned using Group Relative Policy Optimization (GRPO), a [reasoning-oriented variation](https://www.referall.us) of RL. The research study group likewise performed understanding distillation from DeepSeek-R1 to [open-source Qwen](http://106.52.134.223000) and Llama models and released several versions of each

Loading…
Cancel
Save