Pushing the Limits of Large Language Model Quantization via the Linearity Theorem
Paper
• 2411.17525 • Published
• 5
HIGGS
Models prequantized with [HIGGS](https://arxiv.org/abs/2411.17525) zero-shot quantization. Requires the latest `transformers` to run.
-
-
ISTA-DASLab/Llama-3.3-70B-Instruct-HIGGS-GPTQ-4bit
19B • Updated • 25 • 7 -
ISTA-DASLab/Llama-3.1-8B-Instruct-HIGGS-GPTQ-4bit
Text Generation • 3B • Updated • 1 -
ISTA-DASLab/Llama-3.1-8B-Instruct-HIGGS-GPTQ-3bit
Text Generation • 2B • Updated • 1 -
ISTA-DASLab/Llama-3.1-8B-HIGGS-GPTQ-4bit
Text Generation • 3B • Updated • 2 -
ISTA-DASLab/Llama-3.1-8B-HIGGS-GPTQ-3bit
Text Generation • 2B • Updated • 1 -
ISTA-DASLab/Llama-3.3-70B-Instruct-HIGGS-4bit
Text Generation • 19B • Updated • 4 • 3 -
ISTA-DASLab/Llama-3.3-70B-Instruct-HIGGS-3bit
Text Generation • 15B • Updated -
ISTA-DASLab/Llama-3.1-70B-Instruct-HIGGS-4bit
Text Generation • 19B • Updated -
ISTA-DASLab/Llama-3.1-70B-Instruct-HIGGS-3bit
Text Generation • 15B • Updated -
ISTA-DASLab/Llama-3.1-8B-Instruct-HIGGS-4bit
Text Generation • 3B • Updated • 3 -
ISTA-DASLab/Llama-3.1-8B-Instruct-HIGGS-3bit
Text Generation • 2B • Updated • 1 -
ISTA-DASLab/Llama-3.1-8B-HIGGS-4bit
Text Generation • 3B • Updated -
ISTA-DASLab/Llama-3.1-8B-HIGGS-3bit
Text Generation • 2B • Updated • 9 -
ISTA-DASLab/gemma-2-9b-it-HIGGS-4bit
Text Generation • 3B • Updated • 1 • 1 -
ISTA-DASLab/gemma-2-9b-it-HIGGS-3bit
Text Generation • 3B • Updated -
ISTA-DASLab/gemma-2-9b-HIGGS-4bit
Text Generation • 3B • Updated -
ISTA-DASLab/gemma-2-9b-HIGGS-3bit
Text Generation • 3B • Updated • 1