commit 5d24868cc65b0adef1aa8f27541ec94b6fbac881 Author: mitchkrebs775 Date: Fri Feb 21 17:09:11 2025 +0000 Add 'DeepSeek Open-Sources DeepSeek-R1 LLM with Performance Comparable To OpenAI's O1 Model' diff --git a/DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md b/DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md new file mode 100644 index 0000000..9b13421 --- /dev/null +++ b/DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md @@ -0,0 +1,2 @@ +
DeepSeek open-sourced DeepSeek-R1, an LLM fine-tuned with [reinforcement](http://charge-gateway.com) knowing (RL) to [improve thinking](http://47.95.216.250) ability. DeepSeek-R1 attains results on par with OpenAI's o1 design on numerous criteria, [consisting](https://vidhiveapp.com) of MATH-500 and SWE-bench.
+
DeepSeek-R1 is based on DeepSeek-V3, a mix of specialists (MoE) design just recently [open-sourced](http://gogs.oxusmedia.com) by DeepSeek. This base model is fine-tuned using Group Relative Policy Optimization (GRPO), a reasoning-oriented variation of RL. The research team likewise carried out understanding distillation from DeepSeek-R1 to open-source Qwen and [Llama models](https://diversitycrejobs.com) and released numerous versions of each \ No newline at end of file