Update app.py

app.py

@@ -1,6 +1,12 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
+# Load the model and tokenizer outside the function to avoid
+# reloading it on every call.
+model_name = "gustavokuklinski/aeon-360m"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
 def respond(
     message,
@@ -9,40 +15,32 @@ def respond(
     max_tokens,
     temperature,
     top_p,
-    hf_token: gr.OAuthToken,
 ):
-    """
-    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="gustavokuklinski/aeon-360m")
-
     messages = [{"role": "system", "content": system_message}]
-
     messages.extend(history)
-
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
+    # Apply the chat template to format the messages
+    # The jinja template from the model card can be used
+    input_ids = tokenizer.apply_chat_template(
         messages,
-        max_tokens=max_tokens,
-        stream=True,
+        add_generation_prompt=True,
+        return_tensors="pt"
+    )
+
+    # Generate the response
+    outputs = model.generate(
+        input_ids,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+    )
 
-        response += token
-        yield response
+    # Decode the generated text and yield the response
+    response = tokenizer.decode(outputs[0][input_ids.shape[-1]:], skip_special_tokens=True)
+    yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# The rest of your Gradio ChatInterface code remains the same
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
@@ -60,11 +58,5 @@ chatbot = gr.ChatInterface(
     ],
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
 if __name__ == "__main__":
-    demo.launch()
+    chatbot.launch()