-
Notifications
You must be signed in to change notification settings - Fork 38
Issues: gordicaleksa/Open-NLLB
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Preventing some words to be translated
question
Further information is requested
#31
opened Oct 15, 2024 by
ekmekovski
Provide context for input and output
enhancement
New feature or request
help wanted
Extra attention is needed
#29
opened Jan 1, 2024 by
joiemoie
Standard Moroccan Tamazight is mislabeled
documentation
Improvements or additions to documentation
#28
opened Dec 31, 2023 by
MedAymenF
Creation of a small model file for a few languages
question
Further information is requested
#27
opened Nov 4, 2023 by
dlippold
MinHash: benchmark memory, speed and accuracy with varying r and b
enhancement
New feature or request
good first issue
Good for newcomers
#23
opened Sep 29, 2023 by
vienneraphael
[Future - outside current project scope] non-English LLMs (Serbian LLM, etc.)
enhancement
New feature or request
#21
opened Sep 12, 2023 by
gordicaleksa
[Future - outside current project scope] 7B lang-family-specific Open-NLLB checkpoint
enhancement
New feature or request
#20
opened Sep 12, 2023 by
gordicaleksa
[Data] Acquire additional high-quality (non-public) parallel corpora for HBS
enhancement
New feature or request
#19
opened Sep 12, 2023 by
gordicaleksa
[Modeling] Release a 615M English -> HBS Open-NLLB checkpoint
enhancement
New feature or request
#18
opened Sep 12, 2023 by
gordicaleksa
[Modeling] Release a 3.3B Open-NLLB checkpoint (~202 languages)
enhancement
New feature or request
#17
opened Sep 12, 2023 by
gordicaleksa
[Modeling] Release a 1.3B Slavic languages Open-NLLB checkpoint
enhancement
New feature or request
#16
opened Sep 12, 2023 by
gordicaleksa
[Modeling] Release a 615M HBS (Croatian, Bosnian, Serbian) Open-NLLB checkpoint
enhancement
New feature or request
#15
opened Sep 12, 2023 by
gordicaleksa
Get a compute grant
question
Further information is requested
#14
opened Sep 11, 2023 by
gordicaleksa
Estimate the necessary compute and number of GPUs for Open-NLLB effort
documentation
Improvements or additions to documentation
help wanted
Extra attention is needed
#13
opened Sep 11, 2023 by
gordicaleksa
Understand how to do 4-stage curriculum learning from the paper
documentation
Improvements or additions to documentation
help wanted
Extra attention is needed
#12
opened Sep 11, 2023 by
gordicaleksa
Setup a pipeline for mined data (use Allen AI's OSS dataset replication)
enhancement
New feature or request
help wanted
Extra attention is needed
#11
opened Sep 11, 2023 by
gordicaleksa
Obtain high quality Serbian parallel corpus (currently 0 support in our public bi-text)
enhancement
New feature or request
#10
opened Sep 11, 2023 by
gordicaleksa
Choosing the LID model
question
Further information is requested
#8
opened Sep 11, 2023 by
vienneraphael
LID model peak probabilities
question
Further information is requested
#7
opened Sep 11, 2023 by
vienneraphael
Native language visualizations
good first issue
Good for newcomers
question
Further information is requested
#6
opened Sep 11, 2023 by
vienneraphael
Hydra pickle issue in generate_multi.py
bug
Something isn't working
#3
opened Sep 11, 2023 by
vienneraphael
Reduce peak memory when using FSDP on 2+ GPUs
bug
Something isn't working
help wanted
Extra attention is needed
question
Further information is requested
#2
opened Sep 9, 2023 by
gordicaleksa
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.