Edit model card

Official AQLM quantization of meta-llama/Meta-Llama-3-8B .

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

Results:

Model Quantization MMLU (5-shot) ArcC ArcE Hellaswag Winogrande PiQA Model size, Gb
meta-llama/Meta-Llama-3-8B None 0.6525 0.5043 0.8009 0.6019 0.7971 0.7261 16.1
1x16 0.5647 0.4130 0.7428 0.5545 0.7780 0.7198 4.1

UPD 02.05.2024

The version of model with improved fine-tuning procedure.

Downloads last month
100
Safetensors
Model size
2.04B params
Tensor type
FP16
·
I16
·

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