Skip to content
Navigation Menu
Toggle navigation
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Spark
Build and deploy intelligent apps
GitHub Models
Manage and compare prompts
MCP Registry
New
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
BY COMPANY SIZE
Enterprises
Small and medium teams
Startups
Nonprofits
BY USE CASE
App Modernization
DevSecOps
DevOps
CI/CD
View all use cases
BY INDUSTRY
Healthcare
Financial services
Manufacturing
Government
View all industries
View all solutions
Resources
EXPLORE BY TOPIC
AI
Software Development
DevOps
Security
View all topics
EXPLORE BY TYPE
Customer stories
Events & webinars
Ebooks & reports
Business insights
GitHub Skills
SUPPORT & SERVICES
Documentation
Customer support
Community forum
Trust center
Partners
View all resources
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
Accelerator
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
Enterprise platform
AI-powered developer platform
AVAILABLE ADD-ONS
GitHub Advanced Security
Enterprise-grade security features
Copilot for Business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Pricing
Search or jump to...
Search code, repositories, users, issues, pull requests...
Search syntax tips
Provide feedback
Saved searches
Use saved searches to filter your results more quickly
Sign in
Sign up
Appearance settings
Resetting focus
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
slowbull
/
fairseq-py
Public
forked from
facebookresearch/fairseq
Notifications
You must be signed in to change notification settings
Fork
0
Star
0
Code
Pull requests
0
Actions
Projects
Security
0
Insights
Additional navigation options
Code
Pull requests
Actions
Projects
Security
Insights
Commits
Branch selector
master
User selector
All users
All time
Commit History
Commits on Feb 12, 2018
Allow larger maxlen (fixes #100) (#101)
Myle Ott
authored
7e86e30
Copy full SHA for 7e86e30
Commits on Feb 9, 2018
Adjust weight decay by the current learning rate to make it work correctly during annealing
Sergey Edunov
committed
9a95121
Copy full SHA for 9a95121
Commits on Jan 31, 2018
Merge pull request #91 from facebookresearch/prepare_wmt
Show description for e4c935a
Sergey Edunov
authored
e4c935a
Copy full SHA for e4c935a
spelling
Sergey Edunov
committed
52b6119
Copy full SHA for 52b6119
Update README with new models
Sergey Edunov
committed
2c18c27
Copy full SHA for 2c18c27
Merge pull request #95 from bastings/patch-1
Show description for fb36614
Sergey Edunov
authored
fb36614
Copy full SHA for fb36614
Adding README and more parameters to En2De script
Sergey Edunov
committed
971c2d6
Copy full SHA for 971c2d6
Commits on Jan 29, 2018
Ratio should be predlen/reflen not reflen/predlen
Show description for 1ff3efc
Joost Bastings
authored
1ff3efc
Copy full SHA for 1ff3efc
Commits on Jan 27, 2018
Merge branch 'master' of github.com:facebookresearch/fairseq-py into prepare_wmt
Sergey Edunov
committed
d9f46c5
Copy full SHA for d9f46c5
Switch to news-commentary-v12
Sergey Edunov
committed
4185d3e
Copy full SHA for 4185d3e
Commits on Jan 22, 2018
Fixed Weight Decay Regularization in Adam
Show description for ee36a6f
michaelauli
authored and
Myle Ott
committed
ee36a6f
Copy full SHA for ee36a6f
Fix tests
Myle Ott
committed
66d9fcf
Copy full SHA for 66d9fcf
Output correct perplexity when training with --sentence-avg
Myle Ott
committed
f9362e8
Copy full SHA for f9362e8
Fix max_positions calculation in train.py
Myle Ott
committed
81ace09
Copy full SHA for 81ace09
Better warning message for inputs that are too long
Myle Ott
committed
3346943
Copy full SHA for 3346943
ATen Fix
Michael Auli
authored and
Myle Ott
committed
66314a6
Copy full SHA for 66314a6
Momentum correction
Michael Auli
authored and
Myle Ott
committed
173c577
Copy full SHA for 173c577
Report log likelihood for label smoothing
Sergey Edunov
authored and
Myle Ott
committed
dd31fa9
Copy full SHA for dd31fa9
Share input/output embed
Sergey Edunov
authored and
Myle Ott
committed
c537860
Copy full SHA for c537860
Better support for torch.no_grad (since volatile is deprecated)
Myle Ott
committed
907ca92
Copy full SHA for 907ca92
Fix training
Myle Ott
committed
0b84ab1
Copy full SHA for 0b84ab1
Save dictionary in model base classes
Myle Ott
committed
5eddda8
Copy full SHA for 5eddda8
Fix gradient clipping when --clip-norm=0
Myle Ott
committed
08a74a3
Copy full SHA for 08a74a3
Fix LearnedPositionalEmbedding
Myle Ott
committed
fd28c88
Copy full SHA for fd28c88
Move normalization of model output (e.g., via LSM) into model definition
Myle Ott
committed
4db6579
Copy full SHA for 4db6579
Move positional embeddings into LearnedPositionalEmbedding module
Myle Ott
committed
c21a6e2
Copy full SHA for c21a6e2
Fix warning about deprecated `volatile` kwarg for Variables
Myle Ott
committed
185a0df
Copy full SHA for 185a0df
Add option to SequenceGenerator to retain dropout
Myle Ott
committed
dccf790
Copy full SHA for dccf790
Add --max-sentences-valid to train.py
Myle Ott
committed
c542884
Copy full SHA for c542884
Streamline data formatting utils
Myle Ott
committed
eb005cd
Copy full SHA for eb005cd
Add reduce kwarg to criterions
Myle Ott
committed
6f6cb4a
Copy full SHA for 6f6cb4a
Raise FileNotFoundError if dictionary files don't exist
Myle Ott
committed
dcbf5e7
Copy full SHA for dcbf5e7
Output number of model parameters in train.py
Myle Ott
committed
fa50849
Copy full SHA for fa50849
Add explicit dimension to softmax calls
Myle Ott
committed
18a6d85
Copy full SHA for 18a6d85
Support deprecation of volatile Variables in latest PyTorch
Myle Ott
committed
7da4e06
Copy full SHA for 7da4e06
Pagination
Previous
Next
You can’t perform that action at this time.
Myle Ott