Instructions to use google/timesfm-2.5-200m-pytorch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TimesFM
How to use google/timesfm-2.5-200m-pytorch with TimesFM:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Times FM 2.5 model complete model usage example
Hi Guys,
I was using times -2.0-500m model for my app. Unfortunately it was huge more than > 4 GB. So exploring 2.5 model with 200 M .
I want one complete working example with installation steps. Assume i am going to create a Docker image , so i should know each package version. Please note that i can not clone repository. All i can install necessary packages, can download the models etc.
Thanks in advance.
Hello,
I think you can install new version model using the following command:
pip install git+https://github.com/google-research/timesfm.git
In this way, you're not cloning the repository but you're installing all the dependencies in pyproject.toml file.
Hello @lorenzolaudato ,@Ljubomir Josifovski, @MohammedNaeem
I could successfully run TimesFm 2.5 model in my Mac machine. Whereas if i package the same to AWS Lambda, i always get the results as NaN. Tried with multiple way of loading the model and forecast by passing different config, but still no luck. It would be very great if you have AWS Lambda based implementation example. Thank you.
θΏδΈͺ樑εζ―ζε€ειι’ζ΅ε
θΏδΈͺ樑εζ―ζε€ειι’ζ΅ε
https://github.com/google-research/timesfm/issues/30#issuecomment-2126291089