Skip to content

Time Series Forecasting LLM Support #6791

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

Closed
spectral-sequence opened this issue Apr 20, 2024 · 2 comments
Closed

Time Series Forecasting LLM Support #6791

spectral-sequence opened this issue Apr 20, 2024 · 2 comments
Labels
enhancement New feature or request stale

Comments

@spectral-sequence
Copy link

Chronos appears to be a great open source time series forecasting model.
Is it possible to integrate this model into llama.cpp?

https://github.com/amazon-science/chronos-forecasting

@spectral-sequence spectral-sequence added the enhancement New feature or request label Apr 20, 2024
@ngxson
Copy link
Collaborator

ngxson commented Apr 21, 2024

This model uses T5 architecture so we firstly need to support T5, see this issue: #5763

Beside that, this model doesn't have a tokenizer (since time-series signal is converted directly into tokens), so convert script may fail. We can simply add a dummy tokenizer before converting to solve that problem. An example of the HF model (without tokenizer) can be found here: https://huggingface.co/amazon/chronos-t5-small/tree/main

@github-actions github-actions bot added the stale label May 22, 2024
Copy link
Contributor

github-actions bot commented Jun 6, 2024

This issue was closed because it has been inactive for 14 days since being marked as stale.

@github-actions github-actions bot closed this as completed Jun 6, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request stale
Projects
None yet
Development

No branches or pull requests

2 participants