Skip to content

chore: add Moshi #914

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

Merged
merged 3 commits into from
Sep 20, 2024
Merged

chore: add Moshi #914

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0295283
chore: add Moshi
Vaibhavs10 Sep 19, 2024
cf24f15
Merge branch 'main' into vb/add-moshi
Vaibhavs10 Sep 20, 2024
bd17ee4
Merge branch 'main' into vb/add-moshi
Vaibhavs10 Sep 20, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions packages/tasks/src/model-libraries.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -406,6 +406,13 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
filter: false,
countDownloads: `path:"mlc-chat-config.json"`,
},
moshi: {
prettyLabel: "Moshi",
repoName: "Moshi",
repoUrl: "https://github.com/kyutai-labs/moshi",
filter: false,
countDownloads: `path:"tokenizer-e351c8d8-checkpoint125.safetensors"`,
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this looks super specific no?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes! Since there's a mic of safetensors and GGUFs this points to the tokenizer for now - this is the same across all the repos, irrespective of the backend (candle, mlx, PyTorch) - it's the safest way I found without double counting.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Any thoughts about having

Suggested change
countDownloads: `path:"tokenizer-e351c8d8-checkpoint125.safetensors"`,
countDownloads: `path:"model.safetensors" OR path:"model.q4.safetensors" OR path:"model.q8.safetensors" OR path:"model.gguf" OR path:"model.q4.gguf" OR path:"model.q8.gguf"`,

?

It's long and ugly but at least if a new tokenizer is pushed, it won't break the download count. And it wouldn't duplicate counts if I checked correctly.

Otherwise I'm fine with the current solution, there is no perfect one anyway.

},
nemo: {
prettyLabel: "NeMo",
repoName: "NeMo",
Expand Down
Loading