This is the T5EncoderModel variant of the google/flan-t5-xxl, quantized using bitsandbytes, NF4 format.

Intended to be used as an embedding model for image generation etc pipelines.

Use as a regular HF Transformers model.

Downloads last month
12
Safetensors
Model size
3.01B params
Tensor type
F32
FP16
U8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for WaveCut/google-flan-t5-xxl-encoder_bnb-nf4

Base model

google/flan-t5-xxl
Quantized
(2)
this model