MHKetbi/
s1.1-32B:q6_K

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

10 months ago

0e29f83b6eda · 27GB ·

model
qwen2
·
32.8B
·
Q6_K
template
{{- /* System message and tools handling */}} {{- if .Tools}} <|im_start|>system {{- if and (gt (len
system
You are s1.1, created by simplescaling. You are a helpful assistant that can think before reaching f
license
Apache license 2.0
params
{ "num_ctx": 131072, "repeat_penalty": 1.1, "stop": [ "<|im_end|>" ], "t

Readme

Support Me - Donate

pipeline_tag: text-generation

inference: true

license: apache-2.0

datasets: - simplescaling/s1K-1.1

base_model: - Qwen/Qwen2.5-32B-Instruct

library_name: transformers

Model Summary

s1.1 is our sucessor of s1 with better reasoning performance by leveraging reasoning traces from r1 instead of Gemini.

This model is a successor of s1-32B with slightly better performance. Thanks to Ryan Marten for helping generate r1 traces for s1K.

Use

The model usage is documented here.

Evaluation

Metric s1-32B s1.1-32B o1-preview o1 DeepSeek-R1 DeepSeek-R1-Distill-Qwen-32B
# examples 1K 1K ? ? >800K 800K
AIME2024 56.7 >56.7< 40.0 74.4 79.8 72.6
AIME2025 I 26.7 >60.0< 37.5 ? 65.0 46.1
MATH500 93.0 >95.4< 81.4 94.8 97.3 94.3
GPQA-Diamond 59.6 >63.6< 75.2 77.3 71.5 62.1

Note that s1-32B and s1.1-32B use budget forcing in this table; specifically ignoring end-of-thinking and appending “Wait” once or twice.