This is the trained Thinker-Q1.5B model from the paper Thinker: Learning to Think Fast and Slow. Please refer to the GitHub repo for details.

Downloads last month
10
Safetensors
Model size
2B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for stephenchungmh/thinker_q1_5b

Base model

Qwen/Qwen2.5-1.5B
Finetuned
(210)
this model