MHKetbi/
s1.1-32B

80 10 months ago

a reasoning model finetuned from Qwen2.5-32B-Instruct on just 1,000 examples. It matches o1-preview & exhibits test-time scaling via budget forcing. available in [F16, q8_0, q6_K, q4_K_S]

tools

4 models

s1.1-32B:latest
2570713ff25f • 66GB • 32K context window •
Text input • 10 months ago
s1.1-32B:q4_K_S
beec56789fb9 • 19GB • 32K context window •
Text input • 10 months ago
s1.1-32B:q6_K
0e29f83b6eda • 27GB • 32K context window •
Text input • 10 months ago
s1.1-32B:q8_0
79f0f1270a46 • 35GB • 32K context window •
Text input • 10 months ago