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 Bespoke Labs (Ryan Marten) for helping generate r1 traces for s1K with Curator.

Use

The model usage is documented here.


Model is trained with block_size 20000

Downloads last month
8
Safetensors
Model size
1.54B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for TikaToka/s1.1-1.5B-20k

Base model

Qwen/Qwen2.5-1.5B
Finetuned
(361)
this model
Quantizations
2 models

Dataset used to train TikaToka/s1.1-1.5B-20k