fix README.md

README.md

@@ -20,8 +20,10 @@ Run Locally
 1. Python 3.9+
 2. Install deps:
    pip install -r requirements.txt
-3. (Optional) Choose a model (default is a HF-hosted chat model):
-   export HF_MODEL=meta-llama/Meta-Llama-3-8B-Instruct
+3. (Optional) Model selection (default uses GPT‑OSS via Together):
+   export HF_MODEL=openai/gpt-oss-20b
+   # If using GPT‑OSS/Together, set provider key:
+   export TOGETHER_API_KEY=xxxxxxxxxxxxxxxx
 4. Start the app:
    python app.py
 5. Click “Sign in” to grant the app an access token for the Hugging Face Inference API.
@@ -30,7 +32,9 @@ Deploy on Hugging Face Spaces
 1. Create a new Space (SDK: Gradio).
 2. Add files (app.py, requirements.txt, README.md). Push via Git.
 3. Users click “Sign in” to authorize Inference API use.
-4. (Optional) Set `HF_MODEL` in Space Variables to switch models. Prefer HF-hosted chat models (e.g., `meta-llama/Meta-Llama-3-8B-Instruct`, `HuggingFaceH4/zephyr-7b-beta`) to avoid provider permission issues.
+4. (Optional) Set Space Variables:
+   - `HF_MODEL` (e.g., `openai/gpt-oss-20b`)
+   - `TOGETHER_API_KEY` (required for GPT‑OSS via Together)
 
 Persona & Scope
 - Persona: Maya is friendly, busy, non‑technical; answers concretely; asks clarifying questions when prompts are vague.