Time Series Forecasting
Chronos
Safetensors
t5
time series
forecasting
pretrained models
foundation models
time series foundation models
time-series
Instructions to use amazon/chronos-bolt-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Chronos
How to use amazon/chronos-bolt-base with Chronos:
pip install chronos-forecasting
import pandas as pd from chronos import BaseChronosPipeline pipeline = BaseChronosPipeline.from_pretrained("amazon/chronos-bolt-base", device_map="cuda") # Load historical data context_df = pd.read_csv("https://autogluon.s3.us-west-2.amazonaws.com/datasets/timeseries/misc/AirPassengers.csv") # Generate predictions pred_df = pipeline.predict_df( context_df, prediction_length=36, # Number of steps to forecast quantile_levels=[0.1, 0.5, 0.9], # Quantiles for probabilistic forecast id_column="item_id", # Column identifying different time series timestamp_column="Month", # Column with datetime information target="#Passengers", # Column(s) with time series values to predict ) - Notebooks
- Google Colab
- Kaggle
Finetuning model
#1
by fabbrorada - opened
Hi, I tried finetuning the model following https://github.com/amazon-science/chronos-forecasting/blob/main/scripts/README.md but it seems that the procedure is not compatible with bolt models.
Am I wrong? Do you have any plan to extend finetuning to bolt models?
Is there any way I can contribute to this?
Best,
Fabrizio
I've asked the same question in their github repo: https://github.com/amazon-science/chronos-forecasting/discussions/259
Their answer was that there's some fine-tuning capabilities in their autogluon library, but no plans to release low-level training/fine-tuning code like they did for the original Chronos models.