Official AQLM quantization of Mistral-7B-v0.1.
For this quantization, we used 1 codebook of 16 bits.
Results (0-shot acc):
| Model | Quantization | WinoGrande | PiQA | HellaSwag | ArcE | ArcC | Model size, Gb |
|---|---|---|---|---|---|---|---|
| Mistral-7B-v0.1 | None | 0.7364 | 0.8047 | 0.6115 | 0.7887 | 0.4923 | 14.5 |
| 1x16 | 0.6914 | 0.7845 | 0.5745 | 0.7504 | 0.4420 | 2.51 |
To learn more about the inference, as well as the information on how to quantize models yourself, please refer to the official GitHub repo.