import os import urllib.request import gradio as gr from llama_cpp import Llama def download_file(file_link, filename): # Checks if the file already exists before downloading if not os.path.isfile(filename): urllib.request.urlretrieve(file_link, filename) print("File downloaded successfully.") else: print("File already exists.") # Dowloading GGML model from HuggingFace ggml_model_path = "https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GGML/blob/main/codellama-7b-instruct.ggmlv3.Q4_1.bin" filename = "codellama-7b-instruct.ggmlv3.Q4_1.bin" download_file(ggml_model_path, filename) llm = Llama(model_path=filename, n_ctx=512, n_batch=126) 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 llm( 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()