Commit History
[#9] `fetch_pipeline` has been added. Fixed the bug where <pad> tokens will appear in the final output.
47e4017
Update README.md
baf7a1f
unverified
Merge pull request #10 from eubinecto/issue-9
cffca27
unverified
[#9] idiomifier:m-1-3 is ready. main_deploy.py is updated accordingly
c1728bd
[#9] main_deploy.py: removed authors & versions. config.yaml: incresed epochs with smaller lr. fetchers.py: typo fixed
59df933
[#9] updated libraries to their latest versions
72190fb
[#7] training & fetching m-1-3 is ready
ff61478
Merge pull request #8 from eubinecto/issue-7
210581d
unverified
[#7] tokenizer:t-1-1. The tokenizer with the idiom special tokens is now fetchable directly from wandb
12f548d
Merge pull request #6 from eubinecto/issue-5
70f038c
unverified
[#5] idioms:d-1-3 is done. Added multiple senses of the same idiom as a list
370afc1
[#5] literal2idiomatic:d-1-3 done (annotating with special tokens). Some of the data however are erroneous
fca50f9
a couple of explore scripts for: adding two special tokens (<idiom>, </idiom>)
927768a
Merge remote-tracking branch 'origin/main'
c7b4a17
fixing model with eval on deployment
fe34626
Update README.md
6d4b56a
unverified
Merge pull request #3 from eubinecto/issue_2
dfe3d0b
unverified
[#2] updated README.md with a sharable link of streamlit
e589e3d
[#2] minor changes to deploy settings
70bfe2b
[#2] downgrading pandas
122af4f
[#2] deploying the model with `main_deploy.py`.
253de62
[#2] Some simple cleanup
a361918
[#2] Pipeline now supports multiple sentences with batch_decode
08409ff
[#2] typo in paths
6de2ea9
[#2] evaluating m-1-2 works. config.yaml simplified.
642d911
[#2] typo fixed in config.yaml
f49863b
[#2] pandas dependency added
7e3b3a4
[#2] Eval script added. It still needs testing
dd810eb
[#2] Support for d-1-2 done. Support for m-1-2 partially done (need to implement the testing logic with some valid metrics)
e3c7b5a
[#2] refactoring; running transpose subsequently
143c53f
[#1] merging issue_1 to main
2bd8a1e
[#1] the name of the artifact should just be seq2seq
2b6388f
[#1] refactoring: Alpha -> Seq2Seq. We rely on git tags for versioning models.
64a6414
[#1] main_infer.py implemented
6fd648a
[#1] fetch_alpha implemented
322e083
[#1] logging the training loss
d3d3e90
[#1] Alpha implemented
d8d4c8d
[#1] IdiomifyDataModule implemented (srcs, tgts_r, tgts)
25e310b
[#1] SRCBuilder, TGTBuilder implemented and tested
3be6142
[#1] checkpoint before amending builders.py
e9d1a5a
Update README.md
7999e15
unverified
Update README.md
38cf6e8
unverified
saving this branch
207cddf
eubinecto
commited on