Upload chronos_t5_base_200m_forecasting model card

README.md

@@ -0,0 +1,108 @@
+---
+license: apache-2.0
+library_name: ts-arena
+tags:
+- time-series
+- forecasting
+- foundation-model
+- chronos
+- ts-arena
+pipeline_tag: time-series-forecasting
+---
+
+# chronos_t5_base_200m_forecasting
+
+TS Arena wrapper for Amazon Chronos T5-Base time series forecasting model.
+
+## Model Description
+
+Chronos is a family of pretrained time series forecasting models based on language model architectures.
+It tokenizes time series values using scaling and quantization, then uses a T5 model to generate probabilistic forecasts.
+
+| Attribute | Value |
+|-----------|-------|
+| **Parameters** | 200M |
+| **Architecture** | T5 Encoder-Decoder |
+| **Original Repo** | [amazon/chronos-t5-base](https://huggingface.co/amazon/chronos-t5-base) |
+| **Paper** | [Chronos: Learning the Language of Time Series](https://arxiv.org/abs/2403.07815) |
+| **Task** | Time Series Forecasting |
+
+## Usage with TS Arena
+
+```python
+import ts_arena
+
+# Load model
+model = ts_arena.load_model("chronos-t5-base")
+
+# Generate forecasts
+import numpy as np
+context = np.random.randn(96)  # 96 timesteps of history
+output = model.predict(context, prediction_length=24, num_samples=20)
+
+# Access results
+print(output.predictions.shape)      # Point forecasts (median)
+print(output.quantiles[0.5].shape)   # Median forecast
+print(output.quantiles[0.1].shape)   # 10th percentile
+print(output.quantiles[0.9].shape)   # 90th percentile
+```
+
+## Direct Usage with Chronos
+
+```python
+from chronos import ChronosPipeline
+import torch
+
+pipeline = ChronosPipeline.from_pretrained(
+    "amazon/chronos-t5-base",
+    device_map="cuda",
+    torch_dtype=torch.bfloat16,
+)
+
+context = torch.randn(1, 96)  # (batch, time)
+forecast = pipeline.predict(context, prediction_length=24, num_samples=20)
+```
+
+## Evaluation Results
+
+### ETTh1 Dataset (context=96, horizon=96)
+
+| Metric | Value |
+|--------|-------|
+| MSE | 4.37 |
+| MAE | 1.66 |
+| RMSE | 2.09 |
+
+## Features
+
+- **Zero-shot forecasting**: No training required
+- **Probabilistic forecasts**: Returns samples and quantiles
+- **Variable horizons**: Supports different prediction lengths
+- **Multivariate support**: Processes each channel independently
+
+## Limitations
+
+- Univariate model (multivariate handled channel-by-channel)
+- No exogenous variable support
+- Recommended max prediction length: 64
+
+## Citation
+
+```bibtex
+@article{ansari2024chronos,
+  title={Chronos: Learning the Language of Time Series},
+  author={Ansari, Abdul Fatir and Stella, Lorenzo and Turkmen, Caner and Zhang, Xiyuan and others},
+  journal={arXiv preprint arXiv:2403.07815},
+  year={2024}
+}
+```
+
+## License
+
+Apache-2.0 (following the original Chronos license)
+
+## Links
+
+- [TS Arena GitHub](https://github.com/your-username/ts_arena)
+- [Original Chronos](https://github.com/amazon-science/chronos-forecasting)
+- [Chronos Paper](https://arxiv.org/abs/2403.07815)

config.json

@@ -0,0 +1,21 @@
+{
+  "model_type": "chronos",
+  "model_name": "chronos_t5_base_200m_forecasting",
+  "original_repo": "amazon/chronos-t5-base",
+  "parameters": "200M",
+  "architecture": "t5-encoder-decoder",
+  "task": "forecasting",
+  "probabilistic": true,
+  "multivariate": false,
+  "requires_training": false,
+  "context_length": 512,
+  "max_prediction_length": 64,
+  "num_samples": 20,
+  "quantile_levels": [
+    0.1,
+    0.2,
+    0.5,
+    0.8,
+    0.9
+  ]
+}