Update readme

README.md

@@ -1,10 +1,85 @@
 ---
+license: cc-by-nc-4.0
+pipeline_tag: time-series-forecasting
 tags:
-- model_hub_mixin
-- pytorch_model_hub_mixin
+  - time series
+  - forecasting
+  - pretrained models
+  - foundation models
+  - time series foundation models
+  - time-series
 ---
 
-This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
-- Code: [More Information Needed]
-- Paper: [More Information Needed]
-- Docs: [More Information Needed]
+# Moirai-2.0-R-Small
+
+Moirai 2.0 is a decoder-only universal time series forecasting transformer Model pre-trained on:
+- Subset of [GIFT-Eval Pretrain](https://huggingface.co/datasets/Salesforce/GiftEvalPretrain), and [Train](https://huggingface.co/datasets/Salesforce/GiftEval) datasets (Non-leaking historical context). 
+- Mixup data generated from non-leaking subsets of [Chronos Dataset](https://arxiv.org/abs/2403.07815).
+- Synthetic time series produced via KernelSynth introduced in [Chronos paper](https://arxiv.org/abs/2403.07815).
+- Internal Salesforce operational data.
+
+We make significant improvements over the first version of Moirai (please refer to the [paper](https://arxiv.org/abs/2402.02592) for previous version):
+- Switched from a distributional loss to a quantile loss formulation.
+- Moved from single-token to multi-token prediction, improving efficiency and stability.
+- Added a data filtering mechanism to filter out non-forecastable, low quality, time series during pretraining.
+- Added a new patch token embedding which includes missing value information.
+- Added patch-level random mask to improve robustness of the model during inference.
+
+## Usage
+To perform inference with Moirai 2.0, install the uni2ts library from our [GitHub repo](https://github.com/SalesforceAIResearch/uni2ts).
+
+1. Clone repository:
+```shell
+git clone https://github.com/SalesforceAIResearch/uni2ts.git
+cd uni2ts
+```
+
+2) Create virtual environment:
+```shell
+virtualenv venv
+. venv/bin/activate
+```
+
+3) Build from source:
+```shell
+pip install -e '.[notebook]'
+```
+
+4) Create a `.env` file:
+```shell
+touch .env
+```
+
+A simple notebook to get started: [github_notebook_link](https://github.com/SalesforceAIResearch/uni2ts/blob/main/example/moirai_forecast.ipynb)
+
+
+## The Moirai Family
+
+| # Model | # Parameters |
+| :---: | :---: |
+| [Moirai-2.0-R-Small](https://huggingface.co/Salesforce/moirai-1.0-R-small) | 11m |
+| [Moirai-1.0-R-Small](https://huggingface.co/Salesforce/moirai-1.0-R-small) | 14m |
+| [Moirai-1.0-R-Base](https://huggingface.co/Salesforce/moirai-1.0-R-base) | 91m |
+| [Moirai-1.0-R-Large](https://huggingface.co/Salesforce/moirai-1.0-R-large) | 311m |
+
+## Citation
+
+If you're using Uni2TS in your research or applications, please cite it using this BibTeX:
+
+```markdown
+@article{woo2024unified,
+  title={Unified Training of Universal Time Series Forecasting Transformers},
+  author={Woo, Gerald and Liu, Chenghao and Kumar, Akshat and Xiong, Caiming and Savarese, Silvio and Sahoo, Doyen},
+  journal={arXiv preprint arXiv:2402.02592},
+  year={2024}
+}
+```
+
+## Ethical Considerations
+
+This release is for research purposes only in support of an academic paper. 
+Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. 
+We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. 
+We encourage users to consider the common limitations of AI, comply with applicable laws, 
+and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly 
+impact people’s lives, rights, or safety. For further guidance on use cases, refer to our AUP and AI AUP.