Official AQLM quantization of meta-llama/Meta-Llama-3.1-70B-Instruct finetuned with PV-Tuning.

For this quantization, we used 1 codebook of 16 bits and groupsize of 8.

Results:

Model	Quantization	MMLU (5-shot)	ArcC	ArcE	Hellaswag	PiQA	Winogrande	Model size, Gb
	fp16	0.8213	0.6246	0.8683	0.6516	0.8313	0.7908	141
	1x16g8	0.7814	0.5478	0.8270	0.6284	0.8036	0.7814	21.9

Downloads last month: 226

Safetensors

Model size

11B 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-3.1-70B-Instruct-AQLM-PV-2Bit-1x16

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.1-70B-Instruct

Quantized

(95)

this model

Collection including ISTA-DASLab/Meta-Llama-3.1-70B-Instruct-AQLM-PV-2Bit-1x16

AQLM+PV

Collection

Official AQLM quantizations for "PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression": https://arxiv.org/abs/2405.14852 • 25 items • Updated 7 days ago • 19