wassname/multifit

mirror of https://github.com/wassname/multifit.git synced 2026-09-04 16:34:07 +08:00

T

Piotr Czapla 02ee52d0ef Update README.md

2019-09-07 19:11:52 +02:00

Poleval 19 ablation experiments

2019-05-15 18:00:40 +02:00

Clean up the old multfit training code

2019-09-07 15:22:01 +02:00

New bolerplate code

2019-09-07 16:19:09 +02:00

New bolerplate code

2019-09-07 16:19:09 +02:00

Use the pervious datset_path from finetuning for classsificator training

2019-09-07 19:11:29 +02:00

.gitignore

Initial import from fastaiv1

2018-11-08 20:33:10 +01:00

calc_100.sh

Add ability to evalulate multiple models at once

2019-02-12 15:01:01 +01:00

experiment.py

Use the pervious datset_path from finetuning for classsificator training

2019-09-07 19:11:29 +02:00

get_preprocessed_wikis.sh

Download pretrained models

2019-02-15 00:02:04 +01:00

MLDoc.md

Add some results

2019-02-20 10:22:44 +01:00

prepare_cls.py

jp -> ja

2019-02-13 10:50:01 -03:00

prepare_imdb.sh

New bolerplate code

2019-09-07 16:19:09 +02:00

prepare_mldoc.py

Add code to test & train mldoc classifier

2019-02-10 09:52:58 +01:00

prepare_wiki-en.sh

Add script that fetches and prepres WT-2 WT-103

2018-11-15 23:40:50 +01:00

prepare_wiki.sh

prepare_wiki.sh made executable

2019-01-13 17:30:35 +01:00

prepare_xnli.py

Add prepare_xnli.py

2018-11-19 06:50:50 +00:00

prepare_xnli.sh

Minor tweaks.

2018-11-15 23:41:02 +01:00

README.md

Update README.md

2019-09-07 19:11:52 +02:00

requirements.txt

test_end_to_end now working, added instructions to README, sentencepiece dependency

2019-01-22 20:10:38 +01:00

split-cls.py

Add option to remove duplicates

2019-05-14 02:30:25 +02:00

README.md

Retraining a multifit model from wikipedia

The whole training process from wikipedia to mldoc can be run as follows:

python -m experiment new multifit_fp16 \
    pretrain-lm train- data/wiki/de-100 - \
    finetune-lm train- data/mldoc/de-1 - \
    classifier train- data/mldoc/de-1

You can evaulate any model with the following command:

python -m experiment load data/mldoc/de-1/models/fsp15k/multfit_fp16 classifier validate data/mldoc/de-1