DeepSeek: R1 Distill Qwen 1.5B

DeepSeek R1 Distill Qwen 1.5B is a distilled large language model based on Qwen 2.5 Math 1.5B, using outputs from DeepSeek R1. It's a very small and efficient model which outperforms GPT 4o 0513 on Math Benchmarks.

R1 Distill Qwen 1.5B has a 131,072 token context window.

DeepSeek V4 Pro 0813, DeepSeek V4 Flash 0731, DeepSeek V4 Pro 0423 and 9 more are other text models from DeepSeek.

R1 Distill Qwen 1.5B was released on January 31, 2025. Its knowledge cutoff is July 31, 2024.