For this quantization, we used 1 codebook of 16 bits.

Results:

Model	Quantization	MMLU (5-shot)	GSM8k (8-shot)	ArcC	ArcE	Hellaswag	Winogrande	PiQA	Model size, Gb
meta-llama/Meta-Llama-3-8B-Instruct	None	0.6560	0.7475	0.5299	0.8165	0.5771	0.7867	0.7206	16.1
	1x16	0.5872	0.5087	0.4590	0.7710	0.5491	0.7726	0.6953	4.1

UPD 02.05.2024

The version of model with improved fine-tuning procedure.

Downloads last month: 365

Safetensors

Model size

2.04B params

Tensor type

FP16

I16

Inference Examples

Text Generation

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16

Adapters

7 models

Collection including ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16

AQLM

Collection

AQLM quantized LLMs • 20 items • Updated 8 days ago • 46