Update README.md

Aligned with GitHub README

README.md

@@ -21,6 +21,9 @@ covariates. A single checkpoint serves both univariate and multivariate forecast
 operates in a streaming fashion as new observations arrive — all zero-shot, with no
 task-specific training or fine-tuning.
 
+TiRex-2 generalizes our original univariate model, [TiRex](https://huggingface.co/NX-AI/TiRex), to
+multivariate forecasting with past and future covariates.
+
 ## Key facts
 
 - **Zero-shot multivariate forecasting**: 
@@ -34,11 +37,26 @@ task-specific training or fine-tuning.
   TiRex-2 activates 38.4M parameters in univariate mode and an additional 44.1M parameters
   for multivariate forecasting.
 
-# Getting started
+## Getting started
 
 > 📖 For a detailed guide — including pip installation, a Google Colab demo, covariate
 > examples, and benchmark reproduction — see our [GitHub repository](https://github.com/NX-AI/tirex-2).
 
+### Access to Model Weights
+
+TiRex-2's model weights are gated on Hugging Face. To be able to access them, either log in via the Hugging Face CLI, or [generate yourself a Hugging Face access token](https://huggingface.co/settings/tokens/new?canReadGatedRepos=true&tokenType=fineGrained) (make sure to enable Read access to contents of all public gated repos you can access) and set it before loading the model:
+
+CLI:
+```bash
+huggingface-cli login
+```
+
+Access Token:
+
+```bash
+import os
+os.environ["HF_TOKEN"] = "<insert-hf-token>"
+```
 
 The environment is managed by [Pixi](https://pixi.prefix.dev/latest/). Run the following to install it on your machine
 
@@ -66,6 +84,17 @@ We provide predefined Pixi tasks showcasing examplary forecasts. These run in th
 
 For a more **interactive demo of TiRex-2**, we also provide a [quick-start](https://github.com/NX-AI/tirex-2/blob/main/examples/getting_started.ipynb) notebook. 
 
+## TiRex-2 Pro
+TiRex-2 already provides state-of-the-art performance for zero-shot prediction, so you can use this open-source release without training on your own data.
+
+Our pro version extends TiRex-2 with additional capabilities, including:
+
+Streaming: incremental forecast updates as new observations arrive, without recomputing over the full history.
+Speed: performance-optimized inference, including optimization for dedicated hardware such as edge, embedded, and industrial PC deployments.
+Finetuning: models fine-tuned on your data or with different pretraining.
+Classification & Regression: TiRex-2 adapted for classification and regression tasks.
+If you are interested in any of these, please contact us at contact@nx-ai.com.
+
 ## Cite
 If you use TiRex-2 in your research, please cite our work:
 ```bibtex