|
import os |
|
import uuid |
|
|
|
import gradio as gr |
|
|
|
import torch |
|
from transformers import AutoTokenizer |
|
from vllm import AsyncLLMEngine, AsyncEngineArgs, SamplingParams |
|
|
|
MAX_MAX_NEW_TOKENS = 2048 |
|
DEFAULT_MAX_NEW_TOKENS = 1024 |
|
MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096")) |
|
|
|
DESCRIPTION = """\ |
|
# NM vLLM Hermes Mistral Chat |
|
""" |
|
|
|
if not torch.cuda.is_available(): |
|
raise ValueError("Running on CPU 🥶 This demo does not work on CPU.") |
|
|
|
model_id = "neuralmagic/OpenHermes-2.5-Mistral-7B-pruned50" |
|
engine_args = AsyncEngineArgs(model=model_id, sparsity="sparse_w16a16", max_model_len=MAX_INPUT_TOKEN_LENGTH) |
|
engine = AsyncLLMEngine.from_engine_args(engine_args) |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id) |
|
tokenizer.use_default_system_prompt = False |
|
|
|
|
|
async 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, |
|
): |
|
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}) |
|
|
|
formatted_conversation = tokenizer.apply_chat_template(conversation, tokenize=False) |
|
|
|
sampling_params = SamplingParams( |
|
max_tokens=max_new_tokens, |
|
top_p=top_p, |
|
top_k=top_k, |
|
temperature=temperature, |
|
repetition_penalty=repetition_penalty, |
|
) |
|
|
|
stream = await engine.add_request(uuid.uuid4().hex, formatted_conversation, sampling_params) |
|
|
|
async for request_output in stream: |
|
text = request_output.outputs[0].text |
|
yield text |
|
|
|
|
|
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() |
|
|
|
if __name__ == "__main__": |
|
demo.queue(max_size=20).launch() |
