Meta-Llama-Guard-2-8B - bnb 4bit

Description

This model is 4bit quantized version of Meta-Llama-Guard-2-8B using bitsandbytes. It's designed for fine-tuning! The PAD token is set as UNK.

Downloads last month
69
Safetensors
Model size
4.65B params
Tensor type
F32
·
BF16
·
U8
·
Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for leliuga/Meta-Llama-Guard-2-8B-bnb-4bit

Quantized
(9)
this model

Collection including leliuga/Meta-Llama-Guard-2-8B-bnb-4bit