Update README.md

README.md

@@ -139,6 +139,47 @@ Users must log in to their Hugging Face account and obtain access permission bef
 
 For convenience and reproducibility, we recommend downloading MentalBERT locally and replacing the MentalBERT path in the code with the local checkpoint path.
 
+#### 🔐 How to Obtain a Hugging Face Access Token
+
+To download and use gated models (e.g., mental/mental-bert-base-uncased), you need a Hugging Face account and a valid **access token**.
+
+Please follow the steps below:
+
+**Step 1: Create a Hugging Face Account**
+
+If you do not already have one, create an account at:
+  - https://huggingface.co/join
+
+**Step 2: Generate an Access Token**
+
+1. Log in to your Hugging Face account.
+2. Go to **Settings → Access Tokens**.
+3. Click **“Create new token”**.
+4. Choose **Read** permission (this is sufficient for downloading models).
+5. Give the token a name (e.g., `mental-bert-access`).
+6. Click **Create token** and copy the token.
+
+⚠️ Keep your token private. Do not share it or commit it to public repositories.
+
+**Step 3: Log In Programmatically**
+
+Before loading the model, log in using the Hugging Face Hub API:
+
+```python
+from huggingface_hub import login
+
+login()  # Paste your access token when prompted
+```
+This step is required when running code in online environments such as **Google Colab** or remote servers.
+
+**Step 4: Request Access to MentalBERT**
+
+The model `mental/mental-bert-base-uncased` is a gated repository.
+You must explicitly request access on its Hugging Face model page:
+
+- https://huggingface.co/mental/mental-bert-base-uncased
+
+Once access is granted, you will be able to download the model using your access token.
 
 ```python
 import torch