Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
chenpangpang
transformers
Commits
331d8d29
Unverified
Commit
331d8d29
authored
Jun 30, 2020
by
Kevin Canwen Xu
Committed by
GitHub
Jun 30, 2020
Browse files
Upload DistilBART artwork (#5394)
parent
09e84149
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
3 additions
and
0 deletions
+3
-0
examples/seq2seq/README.md
examples/seq2seq/README.md
+3
-0
No files found.
examples/seq2seq/README.md
View file @
331d8d29
## Sequence to Sequence
This directory contains examples for finetuning and evaluating transformers on summarization and translation tasks.
This directory contains examples for finetuning and evaluating transformers on summarization and translation tasks.
Summarization support is more mature than translation support.
Summarization support is more mature than translation support.
Please tag @sshleifer with any issues/unexpected behaviors, or send a PR!
Please tag @sshleifer with any issues/unexpected behaviors, or send a PR!
...
@@ -168,6 +170,7 @@ python run_eval.py sshleifer/distilbart-cnn-12-6 $DATA_DIR/val.source dbart_val_
...
@@ -168,6 +170,7 @@ python run_eval.py sshleifer/distilbart-cnn-12-6 $DATA_DIR/val.source dbart_val_
### DistilBART
### DistilBART

For the CNN/DailyMail dataset, (relatively longer, more extractive summaries), we found a simple technique that works:
For the CNN/DailyMail dataset, (relatively longer, more extractive summaries), we found a simple technique that works:
you just copy alternating layers from
`bart-large-cnn`
and finetune more on the same data.
you just copy alternating layers from
`bart-large-cnn`
and finetune more on the same data.
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment