TimesFM 2.0: Google Open Sources Pre-Trained Model for Time Series Forecasting

General Introduction

TimesFM 2.0 - 500M PyTorch is a pre-trained time series base model developed by Google Research and designed for time series forecasting. The model is capable of handling context lengths up to 2048 points in time and supports arbitrary prediction ranges.TimesFM 2.0 performs well in several leading benchmarks, with a performance improvement of 25% over its predecessor.The model also provides 10 experimental quantile headers, although these headers are not yet calibrated after pre-training. Users can download and use the model for time series forecasting via the Hugging Face platform.

This model can be used in scenarios such as predicting retail sales, stock movements, website traffic, etc. TimesFM 2.0 is ranked #1 on the GIFT-Eval rating list and supports fine-tuning with your own data. It performs univariate time series forecasting for up to 2048 points in time, as well as any forecast range length, with an optional frequency indicator.

Function List

• time series forecast: Supports context lengths up to 2048 time points and arbitrary prediction ranges.
• quantile forecast: 10 experimental quartile heads are provided.
• Model fine-tuning: Support for model fine-tuning on user-owned data.
• Zero sample covariate support: Support for zero-sample prediction using external regression variables.
• High performance: Outperforms in multiple benchmarks with a performance boost of 25%.

Using Help

Installation process

1. Installation of dependencies::
   • utilization pyenv cap (a poem) poetry Perform a local installation.
   • Make sure the Python version is 3.10.x (for JAX versions) or >=3.11.x (for PyTorch versions).
   • Run the following command to install the dependencies:

    pyenv install 3.11.x
   pyenv virtualenv 3.11.x timesfm-env
   pyenv activate timesfm-env
   poetry install
   

2. Download model::
   • Visit the Hugging Face platform to download TimesFM 2.0 - 500M PyTorch Model Checkpoints.
   • Use the following command to download the model: bash
git clone https://huggingface.co/google/timesfm-2.0-500m-pytorch
cd timesfm-2.0-500m-pytorch


Usage Process

1. Loading Models::
   • Load the model in the Python environment:

    from transformers import TimesFMForTimeSeriesForecasting
   model = TimesFMForTimeSeriesForecasting.from_pretrained("google/timesfm-2.0-500m-pytorch")
   

2. carry out forecasting::
   • Prepare input data and make predictions:

    import torch
   input_data = torch.tensor([...])  # Replace with actual time series data
   predictions = model(input_data)
   

3. fine-tuned model::
   • Model fine-tuning using own data:

    from transformers import Trainer, TrainingArguments
   training_args = TrainingArguments(output_dir=". /results", num_train_epochs=3, per_device_train_batch_size=4)
   trainer = Trainer(model=model, args=training_args, train_dataset=your_dataset)
   trainer.train()
   

4. Use of external regression variables::
   • Support for zero-sample covariate prediction: python
external_regressors = torch.tensor([...]) # Replace the data with the actual external regressor variables
predictions = model(input_data, external_regressors=external_regressors)