| import os | |
| from typing import Iterator | |
| import gradio as gr | |
| MAX_MAX_NEW_TOKENS = 2048 | |
| DEFAULT_MAX_NEW_TOKENS = 1024 | |
| MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096")) | |
| DESCRIPTION = """\ | |
| # MIQU-70B | |
| """ | |
| LICENSE = """Pirate license | |
| """ | |
| 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}) | |
| r = requests.post('https://social-warthog-fleet.ngrok-free.app/api/chat', params={ | |
| "model": "miqu", | |
| "messages":conversation, | |
| "stream": false, | |
| "options":{"num_predict": 128, "temperature":1, "top_p":0.95} | |
| }) | |
| outputs = [r.json()['message']['content']] | |
| yield "".join(outputs) | |
| chat_interface = gr.ChatInterface( | |
| fn=generate, | |
| additional_inputs=[ | |
| gr.Textbox(label="System prompt", lines=6), | |
| gr.Slider( | |
| label="Max new tokens", | |
| minimum=1, | |
| maximum=MAX_MAX_NEW_TOKENS, | |
| step=1, | |
| value=DEFAULT_MAX_NEW_TOKENS, | |
| ), | |
| gr.Slider( | |
| label="Temperature", | |
| minimum=0.1, | |
| maximum=4.0, | |
| step=0.1, | |
| value=0.6, | |
| ), | |
| gr.Slider( | |
| label="Top-p (nucleus sampling)", | |
| minimum=0.05, | |
| maximum=1.0, | |
| step=0.05, | |
| value=0.9, | |
| ), | |
| gr.Slider( | |
| label="Top-k", | |
| minimum=1, | |
| maximum=1000, | |
| step=1, | |
| value=50, | |
| ), | |
| gr.Slider( | |
| label="Repetition penalty", | |
| minimum=1.0, | |
| maximum=2.0, | |
| step=0.05, | |
| value=1.2, | |
| ), | |
| ], | |
| 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) | |
| gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button") | |
| chat_interface.render() | |
| gr.Markdown(LICENSE) | |
| if __name__ == "__main__": | |
| demo.queue(max_size=20).launch() | |