This is a 32B reasoning model trained from Qwen2.5-32B-Instruct with 17K data. The performance is on par with o1-preview model on both math and coding.
266 Pulls 2 Tags Updated 1 year ago
Tiny-R1-32B-Preview, which outperforms the 70B model Deepseek-R1-Distill-Llama-70B and nearly matches the full R1 model in math.
1,622 Pulls 6 Tags Updated 1 year ago
Sky-T1-32B-Preview is an experimental research model focused on advancing AI reasoning capabilities
225 Pulls 5 Tags Updated 1 year ago
SuperDistillation Achieves Near-R1 Performance with Just 5% of Parameters, available in [F16, q8_0, q6_K, q4_K_S]
660 Pulls 4 Tags Updated 1 year ago