second commit

app.py

@@ -1,10 +1,7 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
 from llama_cpp import Llama
 
-# Initialize the InferenceClient
-client = InferenceClient()
-
+# Initialize the local model
 llm = Llama.from_pretrained(
     repo_id="ljcamargo/amlonet_llama",
     filename="unsloth.Q4_K_M.gguf",
@@ -29,18 +26,21 @@ def respond(
     messages.append({"role": "user", "content": message})
 
     response = ""
-
-    # Use the client to get the chat completion
-    for message in client.chat_completion(
-        messages,
+    
+    # Use the local model for generation
+    for chunk in llm.create_chat_completion(
+        messages=messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message['choices'][0]['delta']['content']
-        response += token
-        yield response
+        if "choices" in chunk and len(chunk["choices"]) > 0:
+            if "delta" in chunk["choices"][0] and "content" in chunk["choices"][0]["delta"]:
+                token = chunk["choices"][0]["delta"]["content"]
+                if token:
+                    response += token
+                    yield response
 
 demo = gr.ChatInterface(
     respond,