commit
e43cd1386b
1 changed files with 2 additions and 0 deletions
@ -0,0 +1,2 @@ |
|||||
|
<br>[DeepSeek open-sourced](https://3.123.89.178) DeepSeek-R1, an LLM fine-tuned with support learning (RL) to enhance thinking ability. DeepSeek-R1 attains results on par with OpenAI's o1 model on numerous standards, [consisting](https://www.a34z.com) of MATH-500 and [SWE-bench](https://hylpress.net).<br> |
||||
|
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mix of specialists (MoE) design recently open-sourced by DeepSeek. This base design is fine-tuned using Group Relative Policy Optimization (GRPO), a [reasoning-oriented](http://183.221.101.893000) version of RL. The research team also performed understanding [distillation](http://gitlab.hanhezy.com) from DeepSeek-R1 to [open-source Qwen](http://182.92.196.181) and Llama models and [released](http://deve.work3000) a number of variations of each |
Loading…
Reference in new issue