A fine-tuned version of Qwen2.5 32B trained on just 1,000 examples. This version uses R1-generated traces, while the first version uses traces generated by Gemini Flash Thinking. However, the authors found that the R1 traces are longer and more diverse than the Gemini traces.
Specs
Params32B
LicenseApache-2.0
Tags
Similarity · VAIL
VAIL Fingerprint
0050:0069:0088:00bb:00da:0183:081f:6219
Explore other models with behavioral similarity to s1.1-32B.
Adoption · Hugging Face
RAM score
—
Hugging Face Downloads
124
last 30d
74K
all time
HF Likes
99
Relative Adoption Metric contextualizes downloads against the model's size bucket.
Related Models
