# Install transformers from source - only needed for versions <= v4.34 # pip install git+https://github.com/huggingface/transformers.git # pip install accelerate import gradio as gr import torch from transformers import pipeline import os # Load the pipeline pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-beta", torch_dtype=torch.bfloat16, device_map="auto") def respond(user_input, system_message, max_tokens, temperature, top_k, top_p): messages = [ {"role": "system", "content": system_message}, {"role": "user", "content": user_input}, ] prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) outputs = pipe(prompt, max_new_tokens=max_tokens, do_sample=True, temperature=temperature, top_k=top_k, top_p=top_p) return outputs[0]["generated_text"] # Define the Gradio interface demo = gr.Interface( fn=respond, inputs=[ gr.Textbox(lines=2, placeholder="Enter your message here...", label="User Input"), gr.Textbox(value="You are a friendly chatbot who always responds in the style of a pirate", label="System Message"), gr.Slider(minimum=1, maximum=256, value=100, step=1, label="Max New Tokens"), gr.Slider(minimum=0.1, maximum=1.0, value=0.7, step=0.1, label="Temperature"), gr.Slider(minimum=1, maximum=100, value=50, step=1, label="Top-k"), gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p"), ], outputs="text", title="Pirate Chatbot", description="A friendly chatbot who always responds in the style of a pirate.", ) if __name__ == "__main__": demo.launch(share=True) # <|system|> # You are a friendly chatbot who always responds in the style of a pirate. # <|user|> # How many helicopters can a human eat in one sitting? # <|assistant|> # Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!