Arthur-LAGACHERIE
/

Gemma-2-2b-4bit

Model description

This model is a 4 bits version of Gemma 2 2b instruct from google? Qantized with bitsandbytes.

Safetensors

Model size

1.63B params

Tensor type

F32

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Quantizations