kssteven418 / biglittledecoder Goto Github PK

System Info

I try from transformers.models.t5.modeling_t5 import T5_BiLDModel, but it doesn't work. I build the library from transformer repo.

Who can help?

No response

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
• My own task or dataset (give details below)

Reproduction

Just run the translation task. CUDA_VISIBLE_DEVICES=0 python run_bild_translation.py --model bild --small /nobackup/haozhang/BigLittleDecoder/models/smallmodel --large /nobackup/haozhang/BigLittleDecoder/models/bigmodel
--dataset_name iwslt2017 --dataset_config iwslt2017-de-en --source_lang de --target_lang en --bild_rollback 3 --bild_fallback 3

Expected behavior

It can not import the T5BiLDModel

I would like to reproduce a experiment from your paper. If you could share your fine-tuned MT5 and T5 models, it would save me a lot of time and computing resources.

^

System Info

ImportError: cannot import name 'T5BiLDModel' from 'transformers.models.t5.modeling_t5' when run_bild_translation.py

Who can help?

No response

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
• My own task or dataset (give details below)

Reproduction

CUDA_VISIBLE_DEVICES=0 python run_bild_translation.py --model bild --small ../../models/mT5-small-iwslt2017-de-en.bin --large ../../models/mT5-large-iwslt2017-de-en.bin --dataset_name iwslt2017 --dataset_config iwslt2017-de-en --source_lang de --target_lang en --bild_rollback 3 --bild_fallback 2

Expected behavior

build successfully