Update app.py

app.py

@@ -1,64 +1,42 @@
 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, pipeline
+
+# Load tokenizer & model
+model_name = "lewishamilton21/Qwen_1.5B_multilingual_Fine-Tuned_LLM"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
+
+# Text generation pipeline
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer, device_map="auto")
+
+# Chat function
+def chat(user_message, history):
+    # Format prompt from chat history
+    prompt = ""
+    for msg in history:
+        prompt += f"{msg[0]}: {msg[1]}\n"
+    prompt += f"User: {user_message}\nAI:"
+
+    # Generate model response
+    output = generator(prompt, max_length=512, do_sample=True, temperature=0.7, top_p=0.9, num_return_sequences=1)
+    reply = output[0]['generated_text'].split("AI:")[-1].strip()
+
+    # Update history with new message and reply
+    history.append(("User", user_message))
+    history.append(("AI", reply))
+    return history, history
+
+# Gradio app layout
+with gr.Blocks() as demo:
+    gr.Markdown("# 🗣️ Multilingual Qwen 1.5B Chatbot")
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(label="Type your message here...")
+    clear = gr.Button("Clear Chat")
+
+    state = gr.State([])
+
+    msg.submit(chat, [msg, state], [chatbot, state])
+    clear.click(lambda: ([], []), None, [chatbot, state])
+
+# Run the Gradio app
+demo.launch(share=True)