Update app.py

app.py

@@ -1,74 +1,38 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-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
-
-
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load the Hugging Face model and tokenizer
+model_name = "HuggingFaceH4/zephyr-7b-beta"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)
+
+# Define custom system content
+custom_system_content = """
+You are a helpful chatbot designed to assist users with any questions or tasks they may have.
+Please provide thoughtful and concise responses.
+"""
+
+# Function to generate chatbot responses
+def chatbot_response(user_input):
+    inputs = tokenizer(custom_system_content + user_input, return_tensors="pt").to("cuda")
+    outputs = model.generate(**inputs, max_length=256)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response[len(custom_system_content):]
+
+# Gradio Blocks UI
 with gr.Blocks() as demo:
-    system_message = gr.Textbox(
-        label="System Message",
-        value="You are a helpful assistant.",
-        lines=2,
-    )
-    chat_history = gr.State([])
-
     with gr.Row():
-        with gr.Column(scale=0.8):
-            chatbot = gr.Chatbot()
-        with gr.Column(scale=0.2):
-            max_tokens = gr.Slider(
-                minimum=1, maximum=512, step=1, value=128, label="Max Tokens"
-            )
-            temperature = gr.Slider(
-                minimum=0, maximum=1, step=0.01, value=0.7, label="Temperature"
-            )
-            top_p = gr.Slider(
-                minimum=0, maximum=1, step=0.01, value=1, label="Top-p"
-            )
-
-    user_input = gr.Textbox(show_label=False, placeholder="Type your message here...")
+        gr.Markdown("<h2>Zephyr-7B Chatbot</h2>")
+    
+    with gr.Row():
+        with gr.Column():
+            user_input = gr.Textbox(label="Your message", placeholder="Type your message here...")
+            chatbot_output = gr.Textbox(label="Chatbot Response", placeholder="Chatbot will respond here...")
 
-    def user_interaction(message, history, system_message, max_tokens, temperature, top_p):
-        bot_message = next(respond(message, history, system_message, max_tokens, temperature, top_p))
-        history.append((message, bot_message))
-        return history, history
+        with gr.Column():
+            submit_btn = gr.Button("Send")
 
-    user_input.submit(
-        user_interaction,
-        inputs=[user_input, chat_history, system_message, max_tokens, temperature, top_p],
-        outputs=[chatbot, chat_history],
-    )
+    submit_btn.click(fn=chatbot_response, inputs=user_input, outputs=chatbot_output)
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()