Update app.py

app.py

@@ -1,70 +1,43 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    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="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        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
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# MODEL_ID can be any HF model repo you want to load
+MODEL_ID = "meta-llama/Llama-3.2-1B-Instruct"  # replace with your own on the Hub
+
+# load tokenizer + model
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+model = AutoModelForCausalLM.from_pretrained(MODEL_ID)
+
+# chat function
+def chat(input_text, history=[]):
+    # append user input to history
+    history = history or []
+    history.append(("You", input_text))
+
+    # encode input
+    inputs = tokenizer(
+        input_text + tokenizer.eos_token,
+        return_tensors="pt"
+    )
+
+    # generate a response
+    output_ids = model.generate(
+        **inputs,
+        max_new_tokens=100,
+        pad_token_id=tokenizer.eos_token_id
+    )
+
+    response = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+    history.append(("Bot", response))
+
+    # return formatted history
+    return "", history
+
+# Gradio UI
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
+    chatbot = gr.Chatbot()
+    user_input = gr.Textbox(placeholder="Type a message…")
+    user_input.submit(chat, [user_input, chatbot], [user_input, chatbot])
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()