dnrops
/
transformers
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[model cards] fix metadata - 3rd attempt (#7218)

This commit is contained in:
Stas Bekman 2020-09-17 13:57:06 -07:00 committed by GitHub
parent 999a1c957a
commit edbaad2c5c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
12 changed files with 72 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
model_cards/allenai/wmt16-en-de-12-1/README.md
View File

@ -10,11 +10,9 @@ tags:
- allenai
license: Apache 2.0
datasets:
- [main source](http://www.statmt.org/wmt16/)
- [test-set](http://matrix.statmt.org/test_sets/newstest2016.tgz?1504722372)
- wmt16
metrics:
- http://www.statmt.org/wmt16/metrics-task.html
- bleu
---
# FSMT
@ -95,3 +93,7 @@ echo $PAIR
PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py allenai/wmt16-en-de-12-1 $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --num_beams $NUM_BEAMS
```
## Data Sources
- [training, etc.](http://www.statmt.org/wmt16/)
- [test set](http://matrix.statmt.org/test_sets/newstest2016.tgz?1504722372)

10
model_cards/allenai/wmt16-en-de-dist-12-1/README.md
View File

@ -10,11 +10,9 @@ tags:
- allenai
license: Apache 2.0
datasets:
- [main source](http://www.statmt.org/wmt16/)
- [test-set](http://matrix.statmt.org/test_sets/newstest2016.tgz?1504722372)
- wmt16
metrics:
- http://www.statmt.org/wmt16/metrics-task.html
- bleu
---
# FSMT
@ -95,3 +93,7 @@ echo $PAIR
PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py allenai/wmt16-en-de-dist-12-1 $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --num_beams $NUM_BEAMS
```
## Data Sources
- [training, etc.](http://www.statmt.org/wmt16/)
- [test set](http://matrix.statmt.org/test_sets/newstest2016.tgz?1504722372)

10
model_cards/allenai/wmt16-en-de-dist-6-1/README.md
View File

@ -10,11 +10,9 @@ tags:
- allenai
license: Apache 2.0
datasets:
- [main source](http://www.statmt.org/wmt16/)
- [test-set](http://matrix.statmt.org/test_sets/newstest2016.tgz?1504722372)
- wmt16
metrics:
- http://www.statmt.org/wmt16/metrics-task.html
- bleu
---
# FSMT
@ -95,3 +93,7 @@ echo $PAIR
PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py allenai/wmt16-en-de-dist-6-1 $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --num_beams $NUM_BEAMS
```
## Data Sources
- [training, etc.](http://www.statmt.org/wmt16/)
- [test set](http://matrix.statmt.org/test_sets/newstest2016.tgz?1504722372)

9
model_cards/allenai/wmt19-de-en-6-6-base/README.md
View File

@ -11,10 +11,9 @@ tags:
- allenai
license: Apache 2.0
datasets:
- [main source](http://www.statmt.org/wmt19/)
- [test-set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
- wmt19
metrics:
- http://www.statmt.org/wmt19/metrics-task.html
- bleu
---
# FSMT
@ -92,3 +91,7 @@ echo $PAIR
PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py allenai/wmt19-de-en-6-6-base $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --num_beams $NUM_BEAMS
```
## Data Sources
- [training, etc.](http://www.statmt.org/wmt19/)
- [test set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)

9
model_cards/allenai/wmt19-de-en-6-6-big/README.md
View File

@ -11,10 +11,9 @@ tags:
- allenai
license: Apache 2.0
datasets:
- [main source](http://www.statmt.org/wmt19/)
- [test-set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
- wmt19
metrics:
- http://www.statmt.org/wmt19/metrics-task.html
- bleu
---
# FSMT
@ -92,3 +91,7 @@ echo $PAIR
PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py allenai/wmt19-de-en-6-6-big $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --num_beams $NUM_BEAMS
```
## Data Sources
- [training, etc.](http://www.statmt.org/wmt19/)
- [test set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)

9
model_cards/facebook/wmt19-de-en/README.md
View File

@ -10,10 +10,9 @@ tags:
- facebook
license: Apache 2.0
datasets:
- [main source](http://www.statmt.org/wmt19/)
- [test-set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
- wmt19
metrics:
- http://www.statmt.org/wmt19/metrics-task.html
- bleu
---
# FSMT
@ -88,6 +87,10 @@ PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py facebook/w
```
note: fairseq reports using a beam of 50, so you should get a slightly higher score if re-run with `--num_beams 50`.
## Data Sources
- [training, etc.](http://www.statmt.org/wmt19/)
- [test set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
## TODO

9
model_cards/facebook/wmt19-en-de/README.md
View File

@ -10,10 +10,9 @@ tags:
- facebook
license: Apache 2.0
datasets:
- [main source](http://www.statmt.org/wmt19/)
- [test-set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
- wmt19
metrics:
- http://www.statmt.org/wmt19/metrics-task.html
- bleu
---
# FSMT
@ -88,6 +87,10 @@ PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py facebook/w
```
note: fairseq reports using a beam of 50, so you should get a slightly higher score if re-run with `--num_beams 50`.
## Data Sources
- [training, etc.](http://www.statmt.org/wmt19/)
- [test set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
## TODO

9
model_cards/facebook/wmt19-en-ru/README.md
View File

@ -10,10 +10,9 @@ tags:
- facebook
license: Apache 2.0
datasets:
- [main source](http://www.statmt.org/wmt19/)
- [test-set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
- wmt19
metrics:
- http://www.statmt.org/wmt19/metrics-task.html
- bleu
---
# FSMT
@ -88,6 +87,10 @@ PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py facebook/w
```
note: fairseq reports using a beam of 50, so you should get a slightly higher score if re-run with `--num_beams 50`.
## Data Sources
- [training, etc.](http://www.statmt.org/wmt19/)
- [test set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
## TODO

9
model_cards/facebook/wmt19-ru-en/README.md
View File

@ -10,10 +10,9 @@ tags:
- facebook
license: Apache 2.0
datasets:
- [main source](http://www.statmt.org/wmt19/)
- [test-set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
- wmt19
metrics:
- http://www.statmt.org/wmt19/metrics-task.html
- bleu
---
# FSMT
@ -88,6 +87,10 @@ PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py facebook/w
```
note: fairseq reports using a beam of 50, so you should get a slightly higher score if re-run with `--num_beams 50`.
## Data Sources
- [training, etc.](http://www.statmt.org/wmt19/)
- [test set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
## TODO

10
scripts/fsmt/gen-card-allenai-wmt16.py
View File

@ -35,11 +35,9 @@ tags:
- allenai
license: Apache 2.0
datasets:
- [main source](http://www.statmt.org/wmt16/)
- [test-set](http://matrix.statmt.org/test_sets/newstest2016.tgz?1504722372)
- wmt16
metrics:
- http://www.statmt.org/wmt16/metrics-task.html
- bleu
---
# FSMT
@ -120,6 +118,10 @@ echo $PAIR
PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py allenai/{model_name} $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --num_beams $NUM_BEAMS
```
## Data Sources
- [training, etc.](http://www.statmt.org/wmt16/)
- [test set](http://matrix.statmt.org/test_sets/newstest2016.tgz?1504722372)
"""
model_card_dir.mkdir(parents=True, exist_ok=True)
path = os.path.join(model_card_dir, "README.md")

9
scripts/fsmt/gen-card-allenai-wmt19.py
View File

@ -35,10 +35,9 @@ tags:
- allenai
license: Apache 2.0
datasets:
- [main source](http://www.statmt.org/wmt19/)
- [test-set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
- wmt19
metrics:
- http://www.statmt.org/wmt19/metrics-task.html
- bleu
---
# FSMT
@ -116,6 +115,10 @@ echo $PAIR
PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py allenai/{model_name} $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --num_beams $NUM_BEAMS
```
## Data Sources
- [training, etc.](http://www.statmt.org/wmt19/)
- [test set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
"""
model_card_dir.mkdir(parents=True, exist_ok=True)
path = os.path.join(model_card_dir, "README.md")

9
scripts/fsmt/gen-card-facebook-wmt19.py
View File

@ -36,10 +36,9 @@ tags:
- facebook
license: Apache 2.0
datasets:
- [main source](http://www.statmt.org/wmt19/)
- [test-set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
- wmt19
metrics:
- http://www.statmt.org/wmt19/metrics-task.html
- bleu
---
# FSMT
@ -114,6 +113,10 @@ PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py facebook/w
```
note: fairseq reports using a beam of 50, so you should get a slightly higher score if re-run with `--num_beams 50`.
## Data Sources
- [training, etc.](http://www.statmt.org/wmt19/)
- [test set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
## TODO