|
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 = """\ |
|
# Gemma 2 9B IT |
|
Gemma 2 is Google's latest iteration of open LLMs. |
|
This is a demo of [`google/gemma-2-9b-it`](https://huggingface.co/google/gemma-2-9b-it), fine-tuned for instruction following. |
|
For more details, please check [our post](https://huggingface.co/blog/gemma2). |
|
👉 Looking for a larger and more powerful version? Try the 27B version in [HuggingChat](https://huggingface.co/chat/models/google/gemma-2-27b-it). |
|
""" |
|
|
|
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 = "silma-ai/SILMA-Kashif-2B-Instruct-v1.0" |
|
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() |
|
|
|
|
|
@spaces.GPU(duration=90) |
|
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) |
|
|
|
|
|
demo = 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=[ |
|
["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'"], |
|
], |
|
cache_examples=False, |
|
type="messages", |
|
description=DESCRIPTION, |
|
css_paths="style.css", |
|
fill_height=True, |
|
) |
|
|
|
|
|
if __name__ == "__main__": |
|
demo.queue(max_size=20).launch() |
