google
/

flan-t5-large

Text2Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (7)

503 Server Error: Service Unavailable for model 'google/flan-t5-large'

#28 opened 7 days ago by

Request: DOI

#27 opened 2 months ago by

Goggle

#26 opened 6 months ago by

Giving simple information like capital wrong

#25 opened 6 months ago by

very slow output

#24 opened 6 months ago by

bizarre results

#22 opened 8 months ago by

Running the model locally gives a value error.

#21 opened 9 months ago by

[AUTOMATED] Model Memory Requirements

#20 opened about 1 year ago by

model-sizer-bot

Use T5_large for training and output outputs.loss as NAN.

#19 opened about 1 year ago by

Some weights of the model checkpoint at Flan-T5-large were not used when initializing T5ForConditionalGeneration

#18 opened about 1 year ago by

Why 4bit quantised performance is slower than fp 16?

#17 opened about 1 year ago by

Does anyone know the minimum hardware requirements to fine-tune this Flan-T5-Large model?

#16 opened over 1 year ago by

Adding ONNX file of this model

#15 opened almost 2 years ago by

How's T5 handling longer sequences?

#14 opened almost 2 years ago by

Update README.md

#13 opened almost 2 years ago by

name 'init_empty_weights' is not defined

#11 opened almost 2 years ago by

Is 'mps' supported for flans ?

#10 opened almost 2 years ago by

abhishekmamdapure

60 languages?

#8 opened almost 2 years ago by

Is this demo a joke? Look at these horrible results on all kinds of basic and promised tests.

#7 opened about 2 years ago by

BladedSupernova

Failed to reproduce results with CoT on MMLU

#3 opened about 2 years ago by

Hebrew ?encoding? not supported, hebrew translation not functional

#2 opened about 2 years ago by