Official AQLM quantization of google/gemma-2b.
For this quantization, we used 1 codebook of 16 bits.
Results:
| Model | AQLM scheme | WinoGrande | PiQA | HellaSwag | ArcE | ArcC | Model size, Gb |
|---|---|---|---|---|---|---|---|
| gemma-2b | 1x16 | 0.6275 | 0.7318 | 0.4582 | 0.6923 | 0.3259 | 1.7 |
To learn more about the inference, as well as the information on how to quantize models yourself, please refer to the official GitHub repo.