commit
d344e461b3
1 changed files with 2 additions and 0 deletions
@ -0,0 +1,2 @@ |
|||||
|
<br>[DeepSeek open-sourced](https://kol-jobs.com) DeepSeek-R1, an LLM fine-tuned with reinforcement [learning](https://www.graysontalent.com) (RL) to [improve reasoning](http://47.120.20.1583000) ability. DeepSeek-R1 attains outcomes on par with OpenAI's o1 design on several benchmarks, consisting of MATH-500 and SWE-bench.<br> |
||||
|
<br>DeepSeek-R1 is based on DeepSeek-V3, [links.gtanet.com.br](https://links.gtanet.com.br/terilenz4996) a mix of experts (MoE) model recently open-sourced by DeepSeek. This base model is fine-tuned using Group Relative Policy Optimization (GRPO), a reasoning-oriented version of RL. The research group also performed knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama designs and released several versions of each |
Loading…
Reference in new issue