metadata
library_name: transformers
tags:
- phi-3
- phi-3-medium
- phi-3-medium-4k-instruct
- conversational
- text-generation-inference
pipeline_tag: text-generation
language:
- en
Official quantization of Mistral-7B-v0.1 using PV-Tuning on top of AQLM.
For this quantization, we used 1 codebook of 16 bits for groups of 8 weights.
Results (0-shot acc):
Results:
| Model | Quantization | WikiText-2 | C4 | Model size, Gb |
|---|---|---|---|---|
| microsoft/Phi-3-medium-4k-instruct | None | 27.9 | ||
| 1x16g8 (2-bit, this model) | 5.18 | 8.56 | 4.2Gb | |
| 1x16g16 (1-bit, model link) | 7.42 | 10.40 | 2.7Gb |
In general, we always recommend the 2-bit models for best accuracy-size trade-offs. If tempted to use the 1-bit model, try a smaller model , e.g. Phi-3-mini quantized with AQLM+PV (quantized model link) and compare the results, or check our AQLM+PV collection for a more appropriate size.
To learn more about the inference, as well as the information on how to quantize models yourself, please refer to the official GitHub repo. The original code for PV-Tuning can be found in the AQLM@pv-tuning branch.