Official AQLM quantization of meta-llama/Meta-Llama-3-70B-Instruct .

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

Results (measured with lm_eval==4.0):

Model	Quantization	MMLU (5-shot)	ArcC	ArcE	Hellaswag	Winogrande	PiQA	Model size, Gb
meta-llama/Meta-Llama-3-70B	-	0.7980	0.6160	0.8624	0.6367	0.8183	0.7632	141.2
	1x16	0.7587	0.4863	0.7668	0.6159	0.7481	0.7537	21.9

Downloads last month: 464

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-3-70B-Instruct-AQLM-2Bit-1x16

Finetunes

4 models

Quantizations

3 models

Collection including ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16

AQLM

Collection

AQLM quantized LLMs • 20 items • Updated May 3 • 44