Make note about pip vs conda based PyTorch (makes a difference!)

README.md

@@ -29,10 +29,10 @@ To run the Gradio space locally, you first create a sandboxed Python 3.10 enviro
 python -m venv .venv  # <-- Python 3.10
 source .venv/bin/activate
 # OR...
-conda create -n novic_spaces python=3.10
+conda create -y -n novic_spaces python=3.10
 conda activate novic_spaces
 ```
-Then install `gradio` and any further requirements:
+Then install `gradio` and any further requirements (**Note:** A pip-based install of `torch` is actually numerically different than a conda-based install of `pytorch`, which matters for the conda-based pretrained models, but for Hugging Face spaces we do not really have another choice):
 ```bash
 pip install gradio==5.35.0 -r requirements.txt
 ```