Edit model card

gemma-2b-it - bnb 4bit

Description

This model is 4bit quantized version of gemma-2b-it using bitsandbytes. It's designed for fine-tuning! The PAD token is set as "".

Downloads last month
6
Safetensors
Model size
1.55B params
Tensor type
F32
·
BF16
·
U8
·
Inference API
Input a message to start chatting with leliuga/gemma-2b-it-bnb-4bit.
Inference API (serverless) has been turned off for this model.

Quantized from

Collection including leliuga/gemma-2b-it-bnb-4bit