Extreme Compression of Large Language Models via Additive Quantization
Paper
•
2401.06118
•
Published
•
13
AQLM
AQLM quantized LLMs
-
-
ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16
Text Generation • 11B • Updated • 78 • 20 -
ISTA-DASLab/Meta-Llama-3-70B-AQLM-2Bit-1x16
Text Generation • 11B • Updated • 40 • 14 -
ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16
Text Generation • 2B • Updated • 1.83k • 12 -
ISTA-DASLab/Meta-Llama-3-8B-AQLM-2Bit-1x16
Text Generation • 2B • Updated • 81 • 7 -
ISTA-DASLab/c4ai-command-r-v01-AQLM-2Bit-1x16
Text Generation • 6B • Updated • 27 • 10 -
ISTA-DASLab/c4ai-command-r-plus-AQLM-2Bit-1x16
Text Generation • 16B • Updated • 45 • 10 -
ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf
Text Generation • 7B • Updated • 35 • 18 -
ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf
Text Generation • 7B • Updated • 102 • 23 -
ISTA-DASLab/Mistral-7B-Instruct-v0.2-AQLM-2Bit-2x8
Text Generation • 2B • Updated • 86 • 3 -
ISTA-DASLab/Mistral-7B-v0.1-AQLM-2Bit-1x16-hf
Text Generation • 1B • Updated • 16 • 2 -
ISTA-DASLab/gemma-2b-AQLM-2Bit-1x16-hf
Text Generation • 0.8B • Updated • 29 • 6 -
ISTA-DASLab/gemma-2b-AQLM-2Bit-2x8-hf
Text Generation • 1B • Updated • 55 • 4 -
ISTA-DASLab/Llama-2-7b-AQLM-2Bit-1x16-hf
Text Generation • 1B • Updated • 8.06k • 5 -
ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf
Text Generation • 2B • Updated • 1.73k • 2 -
ISTA-DASLab/Llama-2-7b-AQLM-2Bit-8x8-hf
Text Generation • 2B • Updated • 27 -
ISTA-DASLab/Llama-2-13b-AQLM-2Bit-1x16-hf
Text Generation • 2B • Updated • 40 -
ISTA-DASLab/Llama-2-13b-AQLM-4Bit-2x16-hf
Text Generation • Updated • 24 -
ISTA-DASLab/Llama-2-70b-AQLM-2Bit-1x16-hf
Text Generation • 9B • Updated • 17 • 6 -
ISTA-DASLab/Llama-2-70b-AQLM-2Bit-2x8-hf
Text Generation • 18B • Updated • 57 • 1 -
ISTA-DASLab/Llama-2-70b-AQLM-4Bit-2x16-hf
Text Generation • 18B • Updated • 18