Merge pull request #2 from peteryej/codex/update-hf_model-to-nvidia-nemotron-3-nano-30b-a3b-bf16

app.py

@@ -39,7 +39,7 @@ GOOGLE_CLIENT_SECRET = os.environ.get("GOOGLE_CLIENT_SECRET")
 GOOGLE_ALLOWED_DOMAIN = os.environ.get("GOOGLE_ALLOWED_DOMAIN", "").lstrip("@")
 GOOGLE_AUTH_ENABLED = bool(GOOGLE_CLIENT_ID and GOOGLE_CLIENT_SECRET)
 SESSION_SECRET = os.environ.get("SESSION_SECRET", "inside-out-dev-session-secret")
-HF_MODEL =  "google/gemma-4-26B-A4B-it:deepinfra" # "openai/gpt-oss-20b", "Qwen/Qwen3.6-27B:ovhcloud" #
+HF_MODEL = "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16"  # Other models: "google/gemma-4-26B-A4B-it:deepinfra", "openai/gpt-oss-20b", "Qwen/Qwen3.6-27B:ovhcloud"
 SHOW_LOGIN = os.environ.get("SHOW_LOGIN", "").lower() in {"1", "true", "yes"}
 
 # When True, talk to a local llama.cpp server (OpenAI-compatible API) instead of