commit
eb95b8ca5d
1 changed files with 2 additions and 0 deletions
@ -0,0 +1,2 @@ |
|||
<br>DeepSeek open-sourced DeepSeek-R1, an LLM fine-tuned with support learning (RL) to enhance thinking capability. DeepSeek-R1 [attains outcomes](https://uconnect.ae) on par with OpenAI's o1 model on several criteria, consisting of MATH-500 and SWE-bench.<br> |
|||
<br>DeepSeek-R1 is based on DeepSeek-V3, a mixture of experts (MoE) design just recently open-sourced by DeepSeek. This [base design](https://nujob.ch) is fine-tuned using Group Relative Policy Optimization (GRPO), a [reasoning-oriented variation](https://securityjobs.africa) of RL. The research group likewise performed understanding distillation from DeepSeek-R1 to [open-source Qwen](http://121.41.31.1463000) and [Llama models](https://aladin.tube) and [released](http://175.25.51.903000) a number of versions of each |
Loading…
Reference in new issue