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, TextIteratorStreamer | |
DESCRIPTION = """\ | |
# Sahabat-AI Merged | |
This model is merged between GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct and aisingapore/gemma2-9b-cpt-sea-lionv3-instruct | |
This model was merged using the TIES merge method | |
""" | |
MAX_MAX_NEW_TOKENS = 2048 | |
DEFAULT_MAX_NEW_TOKENS = 1024 | |
MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096")) | |
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") | |
model_id = "gmonsoon/gemma2-9b-sahabatai-v1-instruct-BaseTIES" | |
tokenizer = AutoTokenizer.from_pretrained(model_id) | |
model = AutoModelForCausalLM.from_pretrained( | |
model_id, | |
device_map="auto", | |
torch_dtype=torch.bfloat16, | |
) | |
model.config.sliding_window = 4096 | |
model.eval() | |
def generate( | |
message: str, | |
chat_history: list[dict], | |
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 = chat_history.copy() | |
conversation.append({"role": "user", "content": message}) | |
input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, 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, | |
) | |
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.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=[ | |
["Halo, apa kabar?"], | |
["Bisakah anjeun ngajelaskeun singkat naon ari basa pamrograman Python?"], | |
["Jelaskna cerita Cinderella ing sak ukara."], | |
["How many hours does it take a man to eat a Helicopter?"], | |
["Tulislah artikel 100 kata tentang 'Manfaat Open-Source dalam Penelitian AI."], | |
], | |
cache_examples=False, | |
type="messages", | |
) | |
with gr.Blocks(css_paths="style.css", fill_height=True) as demo: | |
gr.Markdown(DESCRIPTION) | |
gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button") | |
chat_interface.render() | |
if __name__ == "__main__": | |
demo.queue(max_size=20).launch() | |