use fine-tuned model

app.py

@@ -14,7 +14,7 @@ def respond(
     """
     For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
     """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
+    client = InferenceClient(token=hf_token.token, model="meta-llama/Meta-Llama-3.1-8B-Instruct-LoRa:phishing-email-adJu",  base_url="https://api.tokenfactory.nebius.com/v1/", api_key="v1.CmQKHHN0YXRpY2tleS1lMDBkMXh2ZDdheDAwNXhxMGgSIXNlcnZpY2VhY2NvdW50LWUwMGp0eHNrM3pubjdyYXQ0azIMCPHv7MgGEJ_k6PEBOgwI8PKElAcQwO2YywNAAloDZTAw.AAAAAAAAAAH-boLssQhDYJht_li9Ql7MN1rSmj_8DXmYlZ13NhdavV0NYylvY_HkVQrALXt2z9Pm5_aQn-tt--Mbc1W8G78E")
 
     messages = [{"role": "system", "content": system_message}]