Jacobian lenses for 4-bit networks
Pre-fitted Jacobian lenses computed through bnb 4-bit quantized networks, for reading and steering 4-bit local deployments.
These are distinct from neuronpedia/jacobian-lens, which were fitted on bf16. These lenses were fitted on 4-bit models, which should help match inference closer.
Each model folder holds lens.pt, its meta.json, and a README with the
source checkpoint, revision, quantization, and fit parameters.
gemma-4-12b-it-qat-q4_0-unquantized: unsloth/gemma-4-12B-it-qat-q4_0-unquantized @f6672c38
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support