Hugging Face's logo

ISTA-DASLab
/
Meta-Llama-3.1-8B-Instruct-AQLM-PV-2Bit-1x16-hf

Text Generation
Transformers
Safetensors
llama
aqlm
facebook
meta
llama-3
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
2
Edit model card

Official AQLM quantization of meta-llama/Meta-Llama-3.1-8B-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
meta-llama/Meta-Llama-3.1-8B-Instruct None 0.6817 0.5162 0.8186 0.5909 0.8014 0.7364 16.1
1x16g8 0.5966 0.4667 0.7790 0.5582 0.7878 0.7001 4.1

Note

We used lm-eval=0.4.0 for evaluation.

UPD (09.08.2024)

Uploaded new version finetuned on more data for longer with better quality.

Downloads last month
130
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-3.1-8B-Instruct-AQLM-PV-2Bit-1x16-hf

Base model

meta-llama/Llama-3.1-8B
Finetuned
meta-llama/Llama-3.1-8B-Instruct
Quantized
(234)
this model

Collection including ISTA-DASLab/Meta-Llama-3.1-8B-Instruct-AQLM-PV-2Bit-1x16-hf