commit f260cf6deede8bb3e426ca7fd4afd60cb7cbda5d Author: derektibbs1730 Date: Fri Feb 21 14:37:03 2025 -0500 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..df7dcf2 --- /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](https://yeetube.com) DeepSeek-R1, an LLM fine-tuned with support knowing (RL) to [enhance thinking](http://117.71.100.2223000) ability. DeepSeek-R1 [attains](https://git.russell.services) results on par with OpenAI's o1 model on numerous benchmarks, including MATH-500 and SWE-bench.
+
DeepSeek-R1 is based upon DeepSeek-V3, a mix of experts (MoE) design recently open-sourced by DeepSeek. This base model is fine-tuned utilizing Group Relative Policy Optimization (GRPO), a reasoning-oriented variation of RL. The research group likewise [performed knowledge](http://119.167.221.1460000) distillation from DeepSeek-R1 to open-source Qwen and Llama models and [released numerous](https://gitlog.ru) versions of each \ No newline at end of file