YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Official AQLM quantization of google/gemma-2b.

For this quantization, we used 2 codebooks of 8 bits.

Results (0-shot acc):

Model Quantization WinoGrande PiQA HellaSwag ArcE ArcC Model size, Gb
gemma-2b None 0.6472 0.7715 0.5279 0.7403 0.4053 5.0
2x8 0.5801 0.6828 0.3891 0.5791 0.2534 1.6

To learn more about the inference, as well as the information on how to quantize models yourself, please refer to the official GitHub repo.

Downloads last month
74
Safetensors
Model size
1.02B params
Tensor type
FP16
·
I8
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Space using ISTA-DASLab/gemma-2b-AQLM-2Bit-2x8-hf 1

Collection including ISTA-DASLab/gemma-2b-AQLM-2Bit-2x8-hf