|
|
|
|
|
import os |
|
from collections.abc import Iterator |
|
from threading import Thread |
|
|
|
import gradio as gr |
|
import spaces |
|
import torch |
|
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer |
|
|
|
DESCRIPTION = "# Llama 3.1 Swallow 8B Instruct V0.3" |
|
|
|
if not torch.cuda.is_available(): |
|
DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>" |
|
|
|
MAX_MAX_NEW_TOKENS = 2048 |
|
DEFAULT_MAX_NEW_TOKENS = 1024 |
|
MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096")) |
|
|
|
if torch.cuda.is_available(): |
|
model_id = "tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3" |
|
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto") |
|
model.eval() |
|
tokenizer = AutoTokenizer.from_pretrained(model_id) |
|
|
|
|
|
@spaces.GPU |
|
@torch.inference_mode() |
|
def generate( |
|
message: str, |
|
chat_history: list[dict], |
|
system_prompt: str = "", |
|
max_new_tokens: int = 1024, |
|
temperature: float = 0.6, |
|
top_p: float = 0.9, |
|
top_k: int = 50, |
|
repetition_penalty: float = 1.0, |
|
) -> Iterator[str]: |
|
conversation = [] |
|
if system_prompt: |
|
conversation.append({"role": "system", "content": system_prompt}) |
|
conversation += chat_history |
|
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=20.0, 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, |
|
pad_token_id=tokenizer.eos_token_id, |
|
) |
|
t = Thread(target=model.generate, kwargs=generate_kwargs) |
|
t.start() |
|
|
|
outputs = [] |
|
for text in streamer: |
|
outputs.append(text) |
|
yield "".join(outputs) |
|
|
|
|
|
demo = gr.ChatInterface( |
|
fn=generate, |
|
additional_inputs_accordion=gr.Accordion(label="詳細設定", open=False), |
|
additional_inputs=[ |
|
gr.Textbox(label="System prompt", value="あなたは誠実で優秀な日本人のアシスタントです。"), |
|
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=2.0, |
|
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=1.0, |
|
), |
|
], |
|
stop_btn=None, |
|
examples=[ |
|
[ |
|
"東京の紅葉した公園で、東京タワーと高層ビルを背景に、空を舞うツバメと草地に佇むラマが出会う温かな物語を書いてください。" |
|
], |
|
], |
|
type="messages", |
|
description=DESCRIPTION, |
|
css_paths="style.css", |
|
fill_height=True, |
|
) |
|
|
|
if __name__ == "__main__": |
|
demo.launch() |
|
|
