Edit model card

An official quantization of meta-llama/Meta-Llama-3-8B using PV-Tuning on top of AQLM .

For this quantization, we used 1 codebook of 16 bits for groups of 8 weights. Note that a large portion of this model are the 16-bit embeddings/logits matrices. You can significantly reduce the model footprint by quantizing these matrices, e.g. using bitsandbytes LLM.int8 or NF4 formats. This does not require additional training

Model AQLM scheme WikiText 2 PPL Model size, Gb Hub link
meta-llama/Meta-Llama-3-8B (this) 1x16g8 6.99 4.1 Link
meta-llama/Meta-Llama-3-8B 1x16g16 9.43 3.9 Link
meta-llama/Meta-Llama-3-70B 1x16g8 4.57 21.9 Link

To learn more about the inference, as well as the information on how to quantize models yourself, please refer to the official GitHub repo. The original code for PV-Tuning can be found in the AQLM@pv-tuning branch.

Downloads last month
45
Safetensors
Model size
2.04B params
Tensor type
FP16
·
I16
·
Inference Examples
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-AQLM-PV-2Bit-1x16

Adapters
1 model

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