Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Evaluate Translation model performance #50

Open
Tracked by #41
svenseeberg opened this issue Oct 1, 2024 · 2 comments · Fixed by #80
Open
Tracked by #41

Evaluate Translation model performance #50

svenseeberg opened this issue Oct 1, 2024 · 2 comments · Fixed by #80
Assignees
@dasgoutam
Labels
analysis Analyse/comparative study of features component:chat Chat Back End
Milestone
v3.2 Improvements...

Comments

@svenseeberg
Copy link
Member

We should try https://huggingface.co/papers/2305.18098 and others.
@svenseeberg svenseeberg added this to the v3 Basic Answer Retrieval milestone Oct 1, 2024
@svenseeberg svenseeberg added analysis Analyse/comparative study of features component:chat Chat Back End labels Oct 1, 2024
@svenseeberg
Copy link
Member Author

svenseeberg commented Oct 9, 2024 •
edited
Loading

Potentially depends on #58 as the model is not directly available with ollama pull. However there is a way to download models from Huggingface manually and serve them locally with Ollama.

@svenseeberg svenseeberg mentioned this issue Nov 13, 2024
Open
5 tasks
@svenseeberg svenseeberg mentioned this issue Nov 22, 2024
Merged
@svenseeberg svenseeberg reopened this Nov 23, 2024
@svenseeberg
Copy link
Member Author

We should check a few more exotic languages. But #80 looks very promising.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@dasgoutam dasgoutam

Labels
analysis Analyse/comparative study of features component:chat Chat Back End
Projects
None yet
Milestone
v3.2 Improvements of Basic Features
Development

Successfully merging a pull request may close this issue.

Use NLLB 200 for translations digitalfabrik/integreat-chat
2 participants
@dasgoutam @svenseeberg