import os from threading import Thread from typing import Iterator import gradio as gr import spaces import torch from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer MAX_MAX_NEW_TOKENS = 2048 DEFAULT_MAX_NEW_TOKENS = 1024 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096")) DESCRIPTION = """\ # Mera Mixture Chat This Space demonstrates model [mera-mix-4x7B](https://huggingface.co/meraGPT/mera-mix-4x7B) by meraGPT, feel free to play with it! """ LICENSE = """
--- created by [meraGPT](https://meraGPT.com) """ if not torch.cuda.is_available(): DESCRIPTION += "\nRunning on CPU 🥶 This demo does not work on CPU.
" if torch.cuda.is_available(): model_id = "meraGPT/mera-mix-4x7B" model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_4bit=True) tokenizer = AutoTokenizer.from_pretrained(model_id) tokenizer.use_default_system_prompt = False @spaces.GPU def generate( message: str, chat_history: list[tuple[str, str]], system_prompt: str, max_new_tokens: int = 1024, temperature: float = 0.6, top_p: float = 0.9, top_k: int = 50, repetition_penalty: float = 1.2, ) -> Iterator[str]: conversation = [] if system_prompt: conversation.append({"role": "system", "content": system_prompt}) for user, assistant in chat_history: conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}]) conversation.append({"role": "user", "content": message}) input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt") if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH: input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:] gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.") input_ids = input_ids.to(model.device) streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True) generate_kwargs = dict( {"input_ids": input_ids}, streamer=streamer, max_new_tokens=max_new_tokens, do_sample=True, top_p=top_p, top_k=top_k, temperature=temperature, num_beams=1, repetition_penalty=repetition_penalty, ) t = Thread(target=model.generate, kwargs=generate_kwargs) t.start() outputs = [] for text in streamer: outputs.append(text) yield "".join(outputs) chat_interface = gr.ChatInterface( fn=generate, additional_inputs=[ gr.Textbox(label="System prompt", lines=6, elem_classes="contain"), gr.Slider( label="Max new tokens", minimum=1, maximum=MAX_MAX_NEW_TOKENS, step=1, value=DEFAULT_MAX_NEW_TOKENS, elem_classes="contain", ), gr.Slider( label="Temperature", minimum=0.1, maximum=4.0, step=0.1, value=0.6, elem_classes="contain", ), gr.Slider( label="Top-p (nucleus sampling)", minimum=0.05, maximum=1.0, step=0.05, value=0.9, elem_classes="contain", ), gr.Slider( label="Top-k", minimum=1, maximum=1000, step=1, value=50, elem_classes="contain", ), gr.Slider( label="Repetition penalty", minimum=1.0, maximum=2.0, step=0.05, value=1.2, elem_classes="contain", ), ], stop_btn=None, examples=[ ["Hello there! How are you doing?"], ["Can you explain briefly to me what is the Python programming language?"], ["Explain the plot of Cinderella in a sentence."], ["How many hours does it take a man to eat a Helicopter?"], ["Write a 100-word article on 'Benefits of Open-Source in AI research'"], ], ) with gr.Blocks(css="style.css") as demo: gr.Markdown(DESCRIPTION,elem_classes="contain") # gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button") chat_interface.render() gr.Markdown(LICENSE,elem_classes="contain") if __name__ == "__main__": demo.queue(max_size=20).launch()