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

master
Albert Gabel 3 months ago
parent
commit
d79eeb4997
  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, [wiki.whenparked.com](https://wiki.whenparked.com/User:HoustonConway) an LLM fine-tuned with reinforcement knowing (RL) to enhance thinking capability. DeepSeek-R1 attains results on par with OpenAI's o1 design on several criteria, including MATH-500 and [SWE-bench](http://h2kelim.com).<br>
<br>DeepSeek-R1 is based on DeepSeek-V3, a mix of specialists (MoE) model recently open-sourced by DeepSeek. This base model is fine-tuned utilizing Group Relative Policy Optimization (GRPO), [setiathome.berkeley.edu](https://setiathome.berkeley.edu/view_profile.php?userid=11986840) a reasoning-oriented variation of RL. The research study group likewise carried out [understanding distillation](https://git.blinkpay.vn) from DeepSeek-R1 to open-source Qwen and Llama models and [released](https://spm.social) several [variations](http://repo.magicbane.com) of each
Loading…
Cancel
Save