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

2 months ago · fcd33e9688
1 changed files with 2 additions and 0 deletions
--- a/DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md
+++ b/DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md
@ -0,0 +1,2 @@
+<br>[DeepSeek open-sourced](https://git.dsvision.net) DeepSeek-R1, an LLM fine-tuned with reinforcement knowing (RL) to enhance reasoning capability. DeepSeek-R1 attains outcomes on par with [OpenAI's](http://gogs.oxusmedia.com) o1 design on several standards, consisting of MATH-500 and SWE-bench.<br>
+<br>DeepSeek-R1 is based upon DeepSeek-V3, a mixture of [specialists](https://seedvertexnetwork.co.ke) (MoE) model just recently open-sourced by DeepSeek. This [base model](http://modiyil.com) is fine-tuned utilizing Group Relative [Policy Optimization](https://mzceo.net) (GRPO), a reasoning-oriented version of RL. The research group also carried out understanding distillation from DeepSeek-R1 to open-source Qwen and Llama models and released a number of variations of each