ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf

Official AQLM quantization of meta-llama/Llama-2-7b-hf.

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

Selected evaluation results for this and other models:

Model	AQLM scheme	WikiText 2 PPL	Model size, Gb	Hub link
Llama-2-7b	1x16	5.92	2.4	Link
Llama-2-7b (THIS)	2x8	6.69	2.2	Link
Llama-2-7b	8x8	6.61	2.2	Link
Llama-2-13b	1x16	5.22	4.1	Link
Llama-2-70b	1x16	3.83	18.8	Link
Llama-2-70b	2x8	4.21	18.2	Link
Mixtral-8x7b	1x16	3.35	12.6	Link
Mixtral-8x7b-Instruct	1x16	-	12.6	Link

UPD (20.02.2024). We applied global finetuning on top of quantized model and improved results compared to first revision.

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