import gradio as gr from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline import torch # --- Load the AI Model --- model_name = "TheBloke/wizardLM-7B-HF" tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained( model_name, device_map="auto", # Uses GPU if available torch_dtype=torch.float16 # Uses half-precision for speed ) chatbot = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=200) # --- Conversation Memory --- history = [] def respond(user_input): if not user_input.strip(): return "" history.append(f"You: {user_input}") prompt = "\n".join(history) response = chatbot(prompt)[0]['generated_text'] history.append(f"AI: {response}") # Format chat history chat_text = "" for msg in history: if msg.startswith("You:"): chat_text += f"
{msg}
" else: chat_text += f"{msg}
" return chat_text def clear_chat(): history.clear() return "" # --- Gradio Interface --- with gr.Blocks() as demo: gr.Markdown("# Study Helper AI") gr.Markdown("Ask me anything! Model: WizardLM-7B-HF (Open Access).") chatbox = gr.HTML() user_input = gr.Textbox(lines=2, placeholder="Type your question here...") send_btn = gr.Button("Send") clear_btn = gr.Button("Clear Chat") send_btn.click(respond, inputs=user_input, outputs=chatbox) clear_btn.click(clear_chat, outputs=chatbox) demo.launch()