Add 'DeepSeek Open-Sources DeepSeek-R1 LLM with Performance Comparable To OpenAI's O1 Model'

2025-02-15 20:10:42 +01:00
commit a910a76f26
1 changed files with 2 additions and 0 deletions
@@ -0,0 +1,2 @@
 <br>[DeepSeek open-sourced](https://owow.chat) DeepSeek-R1, an [LLM fine-tuned](https://gajaphil.com) with reinforcement learning (RL) to enhance thinking [capability](http://1.15.150.903000). DeepSeek-R1 attains [outcomes](http://113.177.27.2002033) on par with [OpenAI's](http://git.jishutao.com) o1 design on a number of benchmarks, [consisting](https://openedu.com) of MATH-500 and SWE-bench.<br>
 <br>DeepSeek-R1 is based upon DeepSeek-V3, a [mixture](https://amorweddfair.com) of professionals (MoE) design just recently open-sourced by DeepSeek. This base model is fine-tuned using Group Relative Policy Optimization (GRPO), a reasoning-oriented variation of RL. The research team also carried out knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama models and launched a number of [versions](https://societeindustrialsolutions.com) of each
		`@@ -0,0 +1,2 @@`
							`<br>[DeepSeek open-sourced](https://owow.chat) DeepSeek-R1, an [LLM fine-tuned](https://gajaphil.com) with reinforcement learning (RL) to enhance thinking [capability](http://1.15.150.903000). DeepSeek-R1 attains [outcomes](http://113.177.27.2002033) on par with [OpenAI's](http://git.jishutao.com) o1 design on a number of benchmarks, [consisting](https://openedu.com) of MATH-500 and SWE-bench.<br>`
							`<br>DeepSeek-R1 is based upon DeepSeek-V3, a [mixture](https://amorweddfair.com) of professionals (MoE) design just recently open-sourced by DeepSeek. This base model is fine-tuned using Group Relative Policy Optimization (GRPO), a reasoning-oriented variation of RL. The research team also carried out knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama models and launched a number of [versions](https://societeindustrialsolutions.com) of each`