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

master
Phillip Foster 2 months ago
commit
362b3f18e6
  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://vacaturebank.vrijwilligerspuntvlissingen.nl) DeepSeek-R1, an [LLM fine-tuned](http://82.157.77.1203000) with reinforcement knowing (RL) to [improve](https://executiverecruitmentltd.co.uk) reasoning ability. DeepSeek-R1 attains results on par with OpenAI's o1 design on a number of benchmarks, [trademarketclassifieds.com](https://trademarketclassifieds.com/user/profile/2672496) consisting of MATH-500 and [SWE-bench](http://metis.lti.cs.cmu.edu8023).<br>
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mix of experts (MoE) model recently [open-sourced](https://samisg.eu8443) by [DeepSeek](https://git.pandaminer.com). This base model is fine-tuned utilizing Group Relative [Policy Optimization](http://git.szchuanxia.cn) (GRPO), a reasoning-oriented version of RL. The research study team also performed knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama designs and released several variations of each
Loading…
Cancel
Save