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

2025-02-09 05:59:19 +01:00
commit 58850ea74d
1 changed files with 2 additions and 0 deletions
@@ -0,0 +1,2 @@
+<br>[DeepSeek open-sourced](https://dztrader.com) DeepSeek-R1, an LLM fine-tuned with [support learning](https://se.mathematik.uni-marburg.de) (RL) to improve thinking ability. DeepSeek-R1 attains results on par with OpenAI's o1 design on a number of standards, consisting of MATH-500 and SWE-bench.<br>
+<br>DeepSeek-R1 is based on DeepSeek-V3, a mix of specialists (MoE) model recently open-sourced by [DeepSeek](http://www.grandbridgenet.com82). This base design is fine-tuned using Group [Relative Policy](https://xn--114-2k0oi50d.com) Optimization (GRPO), a [reasoning-oriented variant](https://upmasty.com) of RL. The research study team likewise carried out knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama models and released a number of [variations](https://git.newpattern.net) of each