gemma-7b - bnb 4bit

Description

This model is 4bit quantized version of gemma-7b using bitsandbytes. It's designed for fine-tuning! The PAD token is set as <>.

Downloads last month
15
Safetensors
Model size
4.78B params
Tensor type
F32
·
BF16
·
U8
·
Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for leliuga/gemma-7b-bnb-4bit

Base model

google/gemma-7b
Quantized
(22)
this model

Collection including leliuga/gemma-7b-bnb-4bit