Spaces:
Running
on
Zero
Running
on
Zero
import os | |
from threading import Thread | |
from typing import Iterator | |
import gradio as gr | |
import spaces | |
import torch | |
from transformers import ( | |
AutoModelForCausalLM, | |
AutoTokenizer, | |
StoppingCriteria, | |
StoppingCriteriaList, | |
TextIteratorStreamer, | |
) | |
class StoppingCriteriaSub(StoppingCriteria): | |
def __init__(self, stops = [], encounters=1): | |
super().__init__() | |
self.stops = [stop.to("cuda") for stop in stops] | |
def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor): | |
last_token = input_ids[0][-1] | |
for stop in self.stops: | |
if tokenizer.decode(stop) == tokenizer.decode(last_token): | |
return True | |
return False | |
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 = "TIGER-Lab/MAmmoTH2-7B-Plus" | |
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto") | |
tokenizer = AutoTokenizer.from_pretrained(model_id) | |
def generate( | |
message: str, | |
chat_history: list[tuple[str, str]], | |
system_prompt: str, | |
max_new_tokens: int = 1024, | |
temperature: float = 0.7, | |
top_p: float = 1.0, | |
repetition_penalty: float = 1.1, | |
) -> 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) | |
stop_words = ["</s>"] | |
stop_words_ids = [tokenizer(stop_word, return_tensors='pt', add_special_tokens=False)['input_ids'].squeeze() for stop_word in stop_words] | |
stopping_criteria = StoppingCriteriaList([StoppingCriteriaSub(stops=stop_words_ids)]) | |
generate_kwargs = dict( | |
{"input_ids": input_ids}, | |
streamer=streamer, | |
max_new_tokens=max_new_tokens, | |
do_sample=True, | |
top_p=top_p, | |
temperature=temperature, | |
num_beams=1, | |
stopping_criteria=stopping_criteria, | |
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), # Adjust width here | |
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=0.01, | |
maximum=1.0, | |
step=0.01, | |
value=0.7, | |
), | |
gr.Slider( | |
label="Top-p (nucleus sampling)", | |
minimum=0.05, | |
maximum=1.0, | |
step=0.01, | |
value=1.0, | |
), | |
gr.Slider( | |
label="Repetition penalty", | |
minimum=1.0, | |
maximum=2.0, | |
step=0.05, | |
value=1.1, | |
), | |
], | |
fill_height=False, | |
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: | |
chat_interface.render() | |
if __name__ == "__main__": | |
demo.queue(max_size=20).launch() |