Adapting the app to our finetuned model.

app.py

@@ -1,20 +1,16 @@
+import os
+from dotenv import load_dotenv
+load_dotenv()
 import gradio as gr
 from huggingface_hub import InferenceClient
 
 """
 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("HuggingFaceH4/zephyr-7b-beta")
+client = InferenceClient(model="Layer7/autotrain-llama32-1b-finetuned", token=os.getenv("HF_TOKEN"))
 
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": system_message}]
 
     for val in history: