s1 is 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.
tools
524 Pulls Updated 8 weeks ago
Updated 8 weeks ago
8 weeks ago
f63fdbd772dd · 20GB
model
archqwen2
·
parameters32.8B
·
quantizationQ4_K_M
20GB
template
{{- if .Suffix }}<|fim_prefix|>{{ .Prompt }}<|fim_suffix|>{{ .Suffix }}<|fim_middle|>
{{- else if .M
1.6kB