From 4b4dcbce552c642f4cb0b556635016e64da577ba Mon Sep 17 00:00:00 2001 From: ulrikeslaughte Date: Fri, 28 Feb 2025 03:08:30 +0800 Subject: [PATCH] Add 'DeepSeek Open-Sources DeepSeek-R1 LLM with Performance Comparable To OpenAI's O1 Model' --- ...R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md | 2 ++ 1 file changed, 2 insertions(+) create mode 100644 DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md 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..5637930 --- /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, [hb9lc.org](https://www.hb9lc.org/wiki/index.php/User:MargieBergin53) an LLM fine-tuned with support knowing (RL) to improve reasoning capability. DeepSeek-R1 attains results on par with [OpenAI's](https://git2.ujin.tech) o1 design on numerous benchmarks, including MATH-500 and [SWE-bench](https://www.genbecle.com).
+
DeepSeek-R1 is based on DeepSeek-V3, a mix of [experts](http://hammer.x0.to) (MoE) design recently [open-sourced](https://www.jgluiggi.xyz) by [DeepSeek](https://www.olindeo.net). This [base model](https://gitea.shoulin.net) is fine-tuned utilizing Group Relative Policy Optimization (GRPO), a [reasoning-oriented variation](https://smaphofilm.com) of RL. The research group likewise carried out [understanding distillation](https://sharingopportunities.com) from DeepSeek-R1 to open-source Qwen and Llama models and [bytes-the-dust.com](https://bytes-the-dust.com/index.php/User:IslaVandermark) released a number of versions of each \ No newline at end of file