Edit model card

Llama-2-13b-chat-hf - bnb 4bit

Description

This model is 4bit quantized version of Llama-2-13b-chat-hf using bitsandbytes. It's designed for fine-tuning! The PAD token is set as UNK.

Downloads last month
3
Safetensors
Model size
6.87B params
Tensor type
F32
·
FP16
·
U8
·
Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for leliuga/Llama-2-13b-chat-hf-bnb-4bit

Quantized
(14)
this model

Collection including leliuga/Llama-2-13b-chat-hf-bnb-4bit