commit
d2e92ba7ce
1 changed files with 2 additions and 0 deletions
@ -0,0 +1,2 @@ |
|||
<br>[DeepSeek open-sourced](http://parasite.kicks-ass.org3000) DeepSeek-R1, an LLM fine-tuned with support learning (RL) to enhance reasoning ability. DeepSeek-R1 attains results on par with OpenAI's o1 model on several benchmarks, [including](http://gogsb.soaringnova.com) MATH-500 and SWE-bench.<br> |
|||
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mix of professionals (MoE) design recently open-sourced by DeepSeek. This [base model](https://raumlaborlaw.com) is fine-tuned using Group Relative Policy Optimization (GRPO), a reasoning-oriented variant of RL. The research study team also [carried](https://sujansadhu.com) out knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama designs and released [numerous variations](https://www.ignitionadvertising.com) of each |
|||
Loading…
Reference in new issue