swadeshb
/

g3-1b-hiper

hierarchical-reasoning

Model card Files Files and versions

g3-1b-hiper

LoRA adapter for the controlled Gemma 3 / T5Gemma 2 hierarchical-SFT experiment.

Base: google/gemma-3-1b-pt
Method: hiper
Training data: sxiong/MLR_structured_trajectory, MATH subset only
LoRA: r=16, alpha=32
Training max length: 8192

Downloads last month: -

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for swadeshb/g3-1b-hiper

Base model

google/gemma-3-1b-pt

Adapter

(60)

this model

Dataset used to train swadeshb/g3-1b-hiper