abwabai
/

madlad400-3b-mt-8bit

Text2Text Generation

Transformers

Safetensors

text-generation-inference

Inference Endpoints

8-bit precision

bitsandbytes

Model card Files Files and versions Community

Edit model card

Model Card for madlad400-3b-mt-8bit

🚨 This model is a 8-bit quantized version of Google's madlad400-3b-mt using bitsandbytes. You can find the unquantized version of madlad400-3b-mt here.

Downloads last month: 14

Safetensors

Model size

2.94B params

Tensor type

F32

FP16

Inference Examples

Text2Text Generation

Inference API (serverless) is not available, repository is disabled.