Upload README.md with huggingface_hub

README.md

@@ -35,6 +35,13 @@ counts are listed in `manifest.json` (`default_year` is used when no year is giv
 
 ## Usage
 
+**Install dependencies** (needs a **GPU**). On Colab/Jupyter prefix with `!`;
+`torch` is already present on Colab, otherwise install the build matching your CUDA:
+
+```bash
+pip install flash-linear-attention==0.5.0 transformers==5.8.1 einops gluonts huggingface_hub
+```
+
 ```python
 from huggingface_hub import snapshot_download
 import sys