Jeethu
/

Llama-3.2-3B-Instruct-PLLM

Text Generation

4-bit precision

Model card Files Files and versions

4-bit OmniQuant quantized version of Llama-3.2-3B-Instruct.

Downloads last month: 15

Model tree for Jeethu/Llama-3.2-3B-Instruct-PLLM

Base model

meta-llama/Llama-3.2-3B-Instruct

Quantized

(458)

this model

Paper for Jeethu/Llama-3.2-3B-Instruct-PLLM

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Paper • 2308.13137 • Published Aug 25, 2023 • 20