Duplicate from amazon/chronos-2

Co-authored-by: Oleksandr Shchur <shchuro@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,155 @@
+---
+license: apache-2.0
+model_id: chronos-2
+tags:
+  - time series
+  - forecasting
+  - foundation models
+  - pretrained models
+  - safetensors
+paper:
+  - https://arxiv.org/abs/2510.15821
+datasets:
+  - autogluon/chronos_datasets
+  - Salesforce/GiftEvalPretrain
+leaderboards:
+  - Salesforce/GIFT-Eval
+  - autogluon/fev-leaderboard
+pipeline_tag: time-series-forecasting
+library_name: chronos-forecasting
+
+---
+
+# Chronos-2
+
+**Update Dec 30, 2025:** ☁️ Deploy Chronos-2 on Amazon SageMaker. [New guide](https://github.com/amazon-science/chronos-forecasting/blob/main/notebooks/deploy-chronos-to-amazon-sagemaker.ipynb) covers real-time GPU and CPU inference, serverless endpoints (run on demand, no idle costs), and batch transform for large-scale forecasting.
+
+**Chronos-2** is a 120M-parameter, encoder-only time series foundation model for zero-shot forecasting.
+It supports **univariate**, **multivariate**, and **covariate-informed** tasks within a single architecture.
+Inspired by the T5 encoder, Chronos-2 produces multi-step-ahead quantile forecasts and uses a group attention mechanism for efficient in-context learning across related series and covariates.
+Trained on a combination of real-world and large-scale synthetic datasets, it achieves **state-of-the-art zero-shot accuracy** among public models on [**fev-bench**](https://huggingface.co/spaces/autogluon/fev-leaderboard), [**GIFT-Eval**](https://huggingface.co/spaces/Salesforce/GIFT-Eval), and [**Chronos Benchmark II**](https://arxiv.org/abs/2403.07815).
+Chronos-2 is also **highly efficient**, delivering over 300 time series forecasts per second on a single A10G GPU and supporting both **GPU and CPU inference**.
+
+## Links
+- 🚀 [Deploy Chronos-2 on Amazon SageMaker](https://github.com/amazon-science/chronos-forecasting/blob/main/notebooks/deploy-chronos-to-amazon-sagemaker.ipynb)
+- 📄 [Technical report](https://arxiv.org/abs/2510.15821v1)
+- 💻 [GitHub](https://github.com/amazon-science/chronos-forecasting)
+- 📘 [Example notebook](https://github.com/amazon-science/chronos-forecasting/blob/main/notebooks/chronos-2-quickstart.ipynb)
+- 📰 [Amazon Science Blog](https://www.amazon.science/blog/introducing-chronos-2-from-univariate-to-universal-forecasting)
+
+
+## Overview
+
+| Capability | Chronos-2 | Chronos-Bolt | Chronos |
+|------------|-----------|--------------|----------|
+| Univariate Forecasting | ✅ | ✅ | ✅ |
+| Cross-learning across items | ✅ | ❌ | ❌ |
+| Multivariate Forecasting | ✅ | ❌ | ❌ |
+| Past-only (real/categorical) covariates | ✅ | ❌ | ❌ |
+| Known future (real/categorical) covariates | ✅ | 🧩 | 🧩 |
+| Max. Context Length | 8192 | 2048 | 512 |
+| Max. Prediction Length | 1024 | 64 | 64 |
+
+🧩 Chronos & Chronos-Bolt do not natively support future covariates, but they can be combined with external covariate regressors (see [AutoGluon tutorial](https://auto.gluon.ai/1.4.0/tutorials/timeseries/forecasting-chronos.html#incorporating-the-covariates)). This only models per-timestep effects, not effects across time. In contrast, Chronos-2 supports all covariate types natively.
+
+
+## Usage
+
+### Local usage
+
+For experimentation and local inference, you can use the [inference package](https://github.com/amazon-science/chronos-forecasting).
+
+Install the package
+```
+pip install "chronos-forecasting>=2.0"
+```
+
+Make zero-shot predictions using the `pandas` API
+
+```python
+import pandas as pd  # requires: pip install 'pandas[pyarrow]'
+from chronos import Chronos2Pipeline
+
+pipeline = Chronos2Pipeline.from_pretrained("amazon/chronos-2", device_map="cuda")
+
+# Load historical target values and past values of covariates
+context_df = pd.read_parquet("https://autogluon.s3.amazonaws.com/datasets/timeseries/electricity_price/train.parquet")
+
+# (Optional) Load future values of covariates
+test_df = pd.read_parquet("https://autogluon.s3.amazonaws.com/datasets/timeseries/electricity_price/test.parquet")
+future_df = test_df.drop(columns="target")
+
+# Generate predictions with covariates
+pred_df = pipeline.predict_df(
+    context_df,
+    future_df=future_df,
+    prediction_length=24,  # Number of steps to forecast
+    quantile_levels=[0.1, 0.5, 0.9],  # Quantiles for probabilistic forecast
+    id_column="id",  # Column identifying different time series
+    timestamp_column="timestamp",  # Column with datetime information
+    target="target",  # Column(s) with time series values to predict
+)
+```
+
+### Deploying a Chronos-2 endpoint to SageMaker
+
+For production use, we recommend deploying Chronos-2 endpoints to Amazon SageMaker.
+
+First, update the SageMaker SDK to make sure that all the latest models are available.
+
+```
+pip install -U sagemaker
+```
+
+Deploy an inference endpoint to SageMaker.
+
+```python
+from sagemaker.jumpstart.model import JumpStartModel
+
+model = JumpStartModel(
+    model_id="pytorch-forecasting-chronos-2",
+    instance_type="ml.g5.2xlarge",
+)
+predictor = model.deploy()
+```
+
+Now you can send time series data to the endpoint in JSON format.
+
+```python
+import pandas as pd
+df = pd.read_csv("https://raw.githubusercontent.com/AileenNielsen/TimeSeriesAnalysisWithPython/master/data/AirPassengers.csv")
+
+payload = {
+    "inputs": [
+        {"target": df["#Passengers"].tolist()}
+    ],
+    "parameters": {
+        "prediction_length": 12,
+    }
+}
+forecast = predictor.predict(payload)["predictions"]
+```
+
+For more details about the endpoint API, check out the [example notebook](https://github.com/amazon-science/chronos-forecasting/blob/main/notebooks/deploy-chronos-to-amazon-sagemaker.ipynb)
+
+
+## Training data
+More details about the training data are available in the [technical report](https://arxiv.org/abs/2510.15821).
+
+- Subset of [Chronos Datasets](https://huggingface.co/datasets/autogluon/chronos_datasets) (excluding test portion of datasets that overlap with GIFT-Eval)
+- Subset of [GIFT-Eval Pretrain](https://huggingface.co/datasets/Salesforce/GiftEvalPretrain)
+- Synthetic univariate and multivariate data
+
+
+## Citation
+
+If you find Chronos-2 useful for your research, please consider citing the associated paper:
+
+```
+@article{ansari2025chronos2,
+  title        = {Chronos-2: From Univariate to Universal Forecasting},
+  author       = {Abdul Fatir Ansari and Oleksandr Shchur and Jaris Küken and Andreas Auer and Boran Han and Pedro Mercado and Syama Sundar Rangapuram and Huibin Shen and Lorenzo Stella and Xiyuan Zhang and Mononito Goswami and Shubham Kapoor and Danielle C. Maddix and Pablo Guerron and Tony Hu and Junming Yin and Nick Erickson and Prateek Mutalik Desai and Hao Wang and Huzefa Rangwala and George Karypis and Yuyang Wang and Michael Bohlke-Schneider},
+  year         = {2025},
+  url          = {https://arxiv.org/abs/2510.15821}
+}
+```

config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Chronos2Model"
+  ],
+  "chronos_config": {
+    "context_length": 8192,
+    "input_patch_size": 16,
+    "input_patch_stride": 16,
+    "max_output_patches": 64,
+    "output_patch_size": 16,
+    "quantiles": [
+      0.01,
+      0.05,
+      0.1,
+      0.15,
+      0.2,
+      0.25,
+      0.3,
+      0.35,
+      0.4,
+      0.45,
+      0.5,
+      0.55,
+      0.6,
+      0.65,
+      0.7,
+      0.75,
+      0.8,
+      0.85,
+      0.9,
+      0.95,
+      0.99
+    ],
+    "time_encoding_scale": 8192,
+    "use_arcsinh": true,
+    "use_reg_token": true
+  },
+  "chronos_pipeline_class": "Chronos2Pipeline",
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 0.05,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_heads": 12,
+  "num_layers": 12,
+  "pad_token_id": 0,
+  "reg_token_id": 1,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 2
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddcda3c7508bf2528087723e98a20707cc04b7f370ae275a9fd88078ddba4f42
+size 477930472