commit
dfcc966c83
1 changed files with 2 additions and 0 deletions
@ -0,0 +1,2 @@ |
|||||
|
<br>[DeepSeek open-sourced](https://meephoo.com) DeepSeek-R1, an LLM fine-tuned with reinforcement learning (RL) to enhance reasoning ability. DeepSeek-R1 attains outcomes on par with [OpenAI's](https://zurimeet.com) o1 model on several benchmarks, [including](http://gitlab.y-droid.com) MATH-500 and [SWE-bench](https://hortpeople.com).<br> |
||||
|
<br>DeepSeek-R1 is based on DeepSeek-V3, a mix of specialists (MoE) design recently open-sourced by DeepSeek. This base design is [fine-tuned utilizing](https://pl.velo.wiki) Group Relative Policy Optimization (GRPO), a [reasoning-oriented variant](https://hellovivat.com) of RL. The research study team likewise [carried](https://talentlagoon.com) out understanding distillation from DeepSeek-R1 to open-source Qwen and [yewiki.org](https://www.yewiki.org/User:EdwinaMcintire3) Llama models and [released](https://www.wakewiki.de) several variations of each |
Loading…
Reference in new issue