Instructions to use Forbu14/meteolibre with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Forbu14/meteolibre with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Forbu14/meteolibre", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Model Card for Model ID
This model is used to do weather forecasting using deep learning.
Model Details
Model Description
- Developed by: Adrien Bufort
- Model type: VAE / video generation model
- License: Apache 2.0
Model Sources [optional]
- Repository: https://github.com/Forbu/meteolibre_model
- Paper [optional]: in the future
- Demo [optional]: in the future
Uses
Use to do weather forecasting
Bias, Risks, and Limitations
THIS IS NOT A CLIMATE MODEL FORECAST
Training Data
Firstly we use the openclimatefix/nimrod-uk-1km dataset from openclimatefix
Evaluation
TO BE DONE IN THE FUTURE
Model Architecture and Objective
Here we will use the classic autoencoder encoder => transformer => decoder architecture.
Compute Infrastructure
We use lightning studio to train the models : https://lightning.ai/
Model Card Authors [optional]
Adrien Bufort
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support