numen-tech
/

Llama-3.3-70B-Instruct-w4a16g128sym

Text Generation

4-bit precision

Model card Files Files and versions

4-bit OmniQuant quantized version of Llama-3.3-70B-Instruct.

Downloads last month: -

Model tree for numen-tech/Llama-3.3-70B-Instruct-w4a16g128sym

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.3-70B-Instruct

Quantized

(158)

this model

Paper for numen-tech/Llama-3.3-70B-Instruct-w4a16g128sym

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Paper • 2308.13137 • Published Aug 25, 2023 • 20