Update app.py

app.py

@@ -1,64 +1,50 @@
 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")
-
-
-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:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    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,
-    ):
-        token = message.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
-"""
-demo = gr.ChatInterface(
-    respond,
-    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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Load model & tokenizer
+model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
+print("Loading model...")
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+print("Model loaded.")
+
+# Global state
+chat_history_ids = None
+chat_step = 0
+
+# Chat function
+def respond(message, history=[]):
+    global chat_history_ids, chat_step
+
+    # Encode user input
+    new_input_ids = tokenizer.encode(message + tokenizer.eos_token, return_tensors="pt")
+
+    # Append to chat history
+    bot_input_ids = (
+        torch.cat([chat_history_ids, new_input_ids], dim=-1)
+        if chat_step > 0 else new_input_ids
+    )
+
+    # Generate response
+    chat_history_ids = model.generate(
+        bot_input_ids,
+        max_new_tokens=500,
+        pad_token_id=tokenizer.eos_token_id,
+        do_sample=True,
+        top_k=50,
+        top_p=0.95,
+        temperature=0.8,
+    )
+
+    # Decode only the newly generated part
+    reply = tokenizer.decode(
+        chat_history_ids[:, bot_input_ids.shape[-1]:][0],
+        skip_special_tokens=True
+    )
+
+    chat_step += 1
+    return reply
+
+# Launch Gradio interface
+gr.ChatInterface(fn=respond, title="🧠 SmolLM Chatbot").launch(share=True)