google/flan-t5-xxl · Discussions

Unable to call this model

1

#70 opened 7 months ago by

Abhi012024

Fix TL;DR TOC link

#69 opened 8 months ago by

ZennyKenny

Classification probabilities

#68 opened 10 months ago by

SaraAmd

Authorization header is correct, but the token seems invalid

24

#67 opened 11 months ago by

Srisowmya

[AUTOMATED] Model Memory Requirements

#65 opened about 1 year ago by

model-sizer-bot

Validation error

#64 opened about 1 year ago by

kishoress1963

While try to using google/flan-t5-xxl inference deploy in AWS sagemaker. Answers is truncated.

3

#62 opened about 1 year ago by

haizamir

can you use it in 'text-generation' instead of 'text-to-text-generation'?

#61 opened about 1 year ago by

surya-narayanan

Autotrain Failures

#60 opened about 1 year ago by

Velhic

Flan-t5-XL and 500 server error

1

#59 opened about 1 year ago by

wendyjboss

Low score and wrong answer for "question-answering" task

#58 opened about 1 year ago by

ybensaid

Config does not align with original paper

#57 opened over 1 year ago by

cbock90

Diversity in beam search

#56 opened over 1 year ago by

ayseozgun

How we can pass System Text?

#55 opened over 1 year ago by

rehan02

maxTokens

2

#54 opened over 1 year ago by

islamn25

ValueError: Need either a `state_dict` or a `save_folder` containing offloaded weights.

5

#53 opened over 1 year ago by

tuannguyends

Cannot finish download of model

1

#52 opened over 1 year ago by

Dipe00

Not getting proper output from this model as before.

3

#50 opened over 1 year ago by

nisha7

🚩 Report

#49 opened over 1 year ago by

barakath

Hey community, Has google flan t5 xxl model updated yesterday ?

#48 opened over 1 year ago by

Aksha

Classifcation

1

#47 opened over 1 year ago by

SaraAmd

input prompt

1

#46 opened over 1 year ago by

SaraAmd

Model google/flan-t5-xxl does not exist

1

#45 opened over 1 year ago by

phdykd

ValueError: Error raised by inference API: Input validation error: `inputs` tokens + `max_new_tokens` must be <= 1512. Given: 190761 `inputs` tokens and 20 `max_new_tokens`

11

#44 opened over 1 year ago by

phdykd

Error raised by inference API: Model google/flan-t5-xl time out

21

#43 opened over 1 year ago by

phdykd

Quoting source from given text for Q&A prompt

3

#42 opened over 1 year ago by

tristanchambers-bids

any plans on increasing model's model_max_length?

17

#41 opened over 1 year ago by

lovodkin93

<Response [422]>

#40 opened over 1 year ago by

skrishna

Output seems overly truncated, and max_length don't seem to matter

12

#39 opened over 1 year ago by

joekr552

Minimum number of tokens in generate

#38 opened over 1 year ago by

rachith

Does the team have the plan to release the multilingual version (60)? When?

#37 opened over 1 year ago by

xin1111

samkenxstream

#34 opened over 1 year ago by

samkenxstream

Flan-T5 tokenizer supports neither Chinese nor many code-related tokens despite being advertised as such

1

#33 opened over 1 year ago by

michaelroyzen

Looking for 'mps' support for flan models ?

#30 opened almost 2 years ago by

abhishekmamdapure

Confusion about sampling for `flan-t5` models

2

#29 opened almost 2 years ago by

ArthurConmy

Add Portuguese in model card tags

1

#28 opened almost 2 years ago by

pierreguillou

file not found error

1

#25 opened almost 2 years ago by

pradeepmohans

Fine tune xxl using 24GB GPU?

7

#23 opened almost 2 years ago by

gameveloster

One gpu version

3

#22 opened almost 2 years ago by

joorei

Float16 and Int8 Produce Wrong Results

7

#21 opened almost 2 years ago by

egeozsoy

Slovak tag instead of Slovenian?

#20 opened almost 2 years ago by

matejklemen

Long variants

#18 opened almost 2 years ago by

fastandthefinetuned

support chinese？

#17 opened almost 2 years ago by

Hines

Clean tokenizer_config.json

#16 opened almost 2 years ago by

skwon

Deploying on Amazon SageMaker

3

#14 opened almost 2 years ago by

ivoschaper

Is there a way to add to the feed my domain specific articles to current trained model?

3

#13 opened almost 2 years ago by

Stromal

run model in colab using 8 bit

8

#8 opened about 2 years ago by

kabalanresearch

Support Japanese?

4

#7 opened about 2 years ago by

kosukekurimoto

Load model automatic in inference API

#6 opened about 2 years ago by

micole66

ValueError: `decoder_start_token_id` or `bos_token_id` has to be defined for encoder-decoder generation

2

#2 opened about 2 years ago by

kosukekurimoto