This repository contains the BitStack-Llama-3-70B model as presented in BitStack: Fine-Grained Size Control for Compressed Large Language Models in Variable Memory Environments.

Downloads last month
12
Safetensors
Model size
142B params
Tensor type
F16
·
U8
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support