google-research/text-to-text-transfer-transformer
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
PythonApache-2.0
Issues
- 0
Clarification on T5 Model Pre-training Objective and Denoising Process
#1121 opened by AliHaiderAhmad001 - 6
ERROR:root:Path not found: gs://t5-data/pretrained_models/large/operative_config.gin
#1084 opened by chattaillaan - 0
Columns and DataType Not Explicitly Set on line 163 of eval_utils_test.py
#1118 opened by CodeSmileBot - 0
Custom Model
#1117 opened by thanhthanhhp123 - 1
- 0
How can I get the best checkpoint in Squad?
#1107 opened by ssoyaavv - 0
Dependencies in `setup.py` have module conflicts.
#1106 opened by unsatisfying - 2
- 2
using A100(40G)*8 gpus server to train T5-3b,it reports OOM resource is exhausted problem
#1043 opened by flyingwaters - 1
- 2
All attempts to get a Google authentication bearer token failed, returning an empty token.
#1092 opened by hwyFighting - 14
TPU VM Training Error - tensorflow.python.framework.errors_impl.NotFoundError: Op type not registered 'SentencepieceOp' in binary running
#965 opened by TambourineMan42 - 1
cmd vs entrypoint youtube video suggestion
#1098 opened by kasiswerreddy - 0
- 0
Question about the metric reported in the paper?
#1091 opened by dsj96 - 0
About "seqio" in "hf_model.py"
#1088 opened by censhallwe - 0
Fine tuning t5 without TPU
#1087 opened by navid72m - 0
how to change teacher forcing fashion to autogressive fashion in training stage?
#1082 opened by estuday - 6
Cannot run setup section of the t5-trivia codelab due to error importing tensorflow_gcs_config
#1027 opened by adelinac - 6
- 1
Predictions are inconsistent unless model is reloaded for each prediction
#1066 opened by coreyfournier - 0
CUDA OOM with HF Model
#1058 opened by fadebek1 - 0
- 0
ValueError when evaluating tuning model using Mtf library
#1040 opened by akku779 - 0
- 3
Can't import T5 module in Colab
#1023 opened by yhong4 - 0
T5 v1.1 downstream results
#1022 opened by eldarkurtic - 4
- 11
Error permission denied model in GCS
#1003 opened by giappham - 1
How should I use an HF model? For any batch_size it gives cuda out of memmory error.
#991 opened by puraminy - 1
HfPyTorchModel usage example not working
#933 opened by mikcnt - 0
t5 version 0.9.3 How to use local sentencepiece.model instead of online to download in some offline environment??
#992 opened by flyingwaters - 1
- 1
C4 fails on Google Dataflow
#986 opened by WenqiJiang - 2
No values in Mixture Registry
#982 opened by JiapengWu - 3
Errors in Deploy Notebook
#970 opened by peregilk - 2
Question on reproducing (Please help me delete this post, posted here by mistake)
#955 opened by zluw1117 - 0
- 4
Colab crashes when running t5-trivia
#937 opened by wehrlean - 0
input with multiple field
#930 opened by zahramahani - 0
- 1
- 0
Bad address
#901 opened by pragna96 - 1
- 1
- 7
Cannot Finetune 11B on Cloud VM
#896 opened by jiachangliu - 3
Colab Notebook : NotFoundError: metrics/_text_similarity_metric_ops.so: undefined symbol:
#874 opened by mmcs-work - 2
Score function usage
#872 opened by antonio-mastropaolo - 1
Can't download GLUE RTE dataset
#871 opened by shunyuzh - 0
Further Pre-training public checkpoint
#868 opened by antonio-mastropaolo