Edit model card

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

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 - 0.7868 0.6041 0.8670 0.6634 0.8248 0.8090 141.2
1x16 0.7486 0.5009 0.7896 0.6346 0.7954 0.7814 21.9
Downloads last month
162
Safetensors
Model size
11B params
Tensor type
FP16
·
I16
·

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