qihoo360/TinyR1-32B-Preview

Warm
Public
32.8B
FP8
32768
2
Feb 24, 2025
License: apache-2.0
Hugging Face

TinyR1-32B-Preview is a 32 billion parameter reasoning model developed by qihoo360, based on the Deepseek-R1-Distill-Qwen-32B architecture. It is specifically optimized for complex reasoning tasks across mathematics, coding, and science domains, demonstrating performance in math that nearly matches larger models. This model was created by fine-tuning and merging domain-specific models to achieve strong overall performance in these analytical areas.

No reviews yet. Be the first to review!