Create app.py

app.py

@@ -0,0 +1,66 @@
+# app.py
+import time
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import gradio as gr
+
+# Load model
+tokenizer = AutoTokenizer.from_pretrained("TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ")
+model = AutoModelForCausalLM.from_pretrained(
+    "TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ",
+    device_map="auto",
+    torch_dtype=torch.float16
+)
+
+# Function to generate AI response
+def generate_response(prompt, chat_history=[]):
+    # Combine history into context
+    context = ""
+    for user_msg, ai_msg in chat_history:
+        context += f"User: {user_msg}\nAI: {ai_msg}\n"
+    context += f"User: {prompt}\nAI:"
+
+    inputs = tokenizer(context, return_tensors="pt").to("cuda")
+    outputs = model.generate(**inputs, max_new_tokens=200, do_sample=True, temperature=0.7)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    
+    # Extract only AI response
+    response = response.split("AI:")[-1].strip()
+    return response
+
+# Simulate live typing
+def live_typing(prompt, chat_history):
+    response = generate_response(prompt, chat_history)
+    displayed_text = ""
+    for char in response:
+        displayed_text += char
+        time.sleep(0.02)  # Typing speed
+        yield displayed_text
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## 🤖 Wizard-Vicuna Chatbot with Avatars and Live Typing")
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            user_avatar = gr.Image("user_avatar.png", elem_id="user-avatar")
+        with gr.Column(scale=4):
+            user_input = gr.Textbox(label="Your Message", placeholder="Type something...")
+            chat_state = gr.State([])  # Keep chat history
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            ai_avatar = gr.Image("ai_avatar.png", elem_id="ai-avatar")
+        with gr.Column(scale=4):
+            output_box = gr.Textbox(label="AI is typing...", lines=8)
+
+    def chat(user_message, history):
+        # Append AI response after live typing
+        for partial in live_typing(user_message, history):
+            yield partial, history
+        history.append((user_message, partial))
+        yield partial, history
+
+    user_input.submit(chat, inputs=[user_input, chat_state], outputs=[output_box, chat_state])
+
+demo.launch()