Official AQLM quantization of meta-llama/Meta-Llama-3.1-8B-Instruct finetuned with PV-Tuning.

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

Results:

Model	Quantization	MMLU (5-shot)	ArcC	ArcE	Hellaswag	PiQA	Winogrande	Model size, Gb
meta-llama/Meta-Llama-3.1-8B-Instruct	None	0.6817	0.5162	0.8186	0.5909	0.8014	0.7364	16.1
	2x8g8	0.5533	0.4531	0.7757	0.5459	0.7835	0.7064	3.9

Note

We used lm-eval=0.4.0 for evaluation.

Downloads last month: 22

Safetensors

Model size

2.8B params

Tensor type

FP16

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.

Collection including ISTA-DASLab/Meta-Llama-3.1-8B-Instruct-AQLM-PV-2Bit-2x8-hf

AQLM+PV

Collection

Official AQLM quantizations for "PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression": https://arxiv.org/abs/2405.14852 • 21 items • Updated Sep 18 • 18