justheuristic's picture
Update README.md
8698971 verified
metadata
library_name: transformers
tags:
  - llama
  - facebook
  - meta
  - llama-2
  - conversational
  - text-generation-inference

An official quantization of meta-llama/Llama-2-7b using PV-Tuning on top of AQLM.

For this quantization, we used 2 codebooks of 8 bits each for groups of 8 weights.

Model AQLM scheme WikiText 2 PPL Model size, Gb Hub link
Llama-2-7b 1x16 5.68 2.4 Link
Llama-2-7b (this) 2x8 5.90 2.2 Link
Llama-2-7b 1x16g16 9.21 1.7 Link
Llama-2-13b 1x16 5.05 4.1 Link
Llama-2-70b 1x16 3.78 18.8 Link

The 1x16g16 (1-bit) models are on the way, as soon as we update the inference lib with their respective kernels.

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.