altpuppet commited on
Commit
d0f7d8b
Β·
1 Parent(s): 8394e95

Add Hugging Face Spaces configuration: requirements.txt and Spaces metadata in README.md

Browse files
Files changed (2) hide show
  1. README.md +30 -0
  2. requirements.txt +19 -0
README.md CHANGED
@@ -1,3 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  # TempoPFN: Synthetic Pre-Training of Linear RNNs for Zero-Shot Time Series Forecasting
2
 
3
  [![preprint](https://img.shields.io/static/v1?label=Paper&message=2509.26468&color=B31B1B&logo=arXiv)](https://arxiv.org/abs/2510.25502) [![GIFT-Eval](https://img.shields.io/badge/%F0%9F%8F%86%20GIFT--Eval-Leaderboard-0078D4)](https://huggingface.co/spaces/Salesforce/GIFT-Eval) [![huggingface](https://img.shields.io/badge/%F0%9F%A4%97%20HF-Model_Repo-FFD21E)](https://huggingface.co/AutoML-org/TempoPFN) [![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-green.svg)](https://github.com/automl/TempoPFN/blob/main/LICENSE)
 
1
+ ---
2
+ title: TempoPFN Forecasting Terminal
3
+ emoji: πŸŒ–
4
+ colorFrom: green
5
+ colorTo: purple
6
+ sdk: gradio
7
+ sdk_version: 5.49.1
8
+ app_file: app.py
9
+ pinned: false
10
+ python_version: '3.12'
11
+ license: apache-2.0
12
+ ---
13
+
14
+ # TempoPFN: Zero-Shot Forecasting & Analysis Terminal
15
+
16
+ ## πŸš€ What is this Space?
17
+
18
+ **Interactive TempoPFN Application** - A comprehensive zero-shot time series forecasting platform featuring:
19
+
20
+ ### πŸ“Š 4 Main Features:
21
+ 1. **Financial Markets** - Stock analysis, technical indicators, volatility tracking with real market data
22
+ 2. **Research & Analysis** - Synthetic data forecasting with advanced statistical analysis
23
+ 3. **Synthetic Data Generation** - 12+ generator types with customizable parameters
24
+ 4. **GIFT Evaluation** - Standardized benchmark framework for model evaluation
25
+
26
+ ### ✨ Built on TempoPFN
27
+ This application is powered by [TempoPFN](https://huggingface.co/AutoML-org/TempoPFN), a state-of-the-art time series foundation model pretrained entirely on synthetic data. It delivers top-tier zero-shot forecasting accuracy while remaining fully reproducible.
28
+
29
+ ---
30
+
31
  # TempoPFN: Synthetic Pre-Training of Linear RNNs for Zero-Shot Time Series Forecasting
32
 
33
  [![preprint](https://img.shields.io/static/v1?label=Paper&message=2509.26468&color=B31B1B&logo=arXiv)](https://arxiv.org/abs/2510.25502) [![GIFT-Eval](https://img.shields.io/badge/%F0%9F%8F%86%20GIFT--Eval-Leaderboard-0078D4)](https://huggingface.co/spaces/Salesforce/GIFT-Eval) [![huggingface](https://img.shields.io/badge/%F0%9F%A4%97%20HF-Model_Repo-FFD21E)](https://huggingface.co/AutoML-org/TempoPFN) [![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-green.svg)](https://github.com/automl/TempoPFN/blob/main/LICENSE)
requirements.txt ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ gradio>=5.49.1
2
+ numpy>=1.21.0
3
+ pandas>=1.3.0
4
+ torch>=2.1.0
5
+ huggingface-hub>=0.20.0
6
+ yfinance>=0.2.0
7
+ pandas-ta>=0.3.14b0
8
+ plotly>=5.0.0
9
+ scipy>=1.7.0
10
+ scikit-learn>=1.0.0
11
+ statsmodels>=0.13.0
12
+ datasets>=2.0.0
13
+ linear-operator>=0.5.0
14
+ gluonts>=0.15.0
15
+ tqdm>=4.62.0
16
+ requests>=2.25.0
17
+ python-dateutil>=2.8.0
18
+ pytz>=2021.1
19
+ PyYAML>=5.4.1