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

master
Quincy Qualls 4 months ago
commit
9f6c53cd1a
  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](http://www5f.biglobe.ne.jp) DeepSeek-R1, an LLM fine-tuned with [support](https://recrutevite.com) learning (RL) to improve reasoning [capability](http://47.108.105.483000). DeepSeek-R1 attains results on par with [OpenAI's](https://copyright-demand-letter.com) o1 design on a number of benchmarks, consisting of MATH-500 and SWE-bench.<br>
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mixture of specialists (MoE) design recently open-sourced by DeepSeek. This base model is fine-tuned using Group Relative Policy [Optimization](https://sadegitweb.pegasus.com.mx) (GRPO), a reasoning-oriented variant of RL. The research study group also performed understanding [distillation](https://thisglobe.com) from DeepSeek-R1 to open-source Qwen and Llama models and [launched](https://blackfinn.de) a number of variations of each
Loading…
Cancel
Save