File size: 2,794 Bytes
702ff78 0cf00a8 702ff78 4e7dc13 702ff78 7fce000 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 |
import os
os.system("pip install git+https://github.com/shumingma/transformers.git")
import threading
import torch
import torch._dynamo
torch._dynamo.config.suppress_errors = True
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
TextIteratorStreamer,
)
import gradio as gr
model_id = "microsoft/bitnet-b1.58-2B-4T"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16).to("cpu")
def respond(
message: str,
history: list[tuple[str,str]],
system_message: str,
max_tokens: int,
temperature: float,
top_p: float,
):
messages = [{"role": "system", "content": system_message}]
for user_msg, bot_msg in history:
if user_msg:
messages.append({"role": "user", "content": user_msg})
if bot_msg:
messages.append({"role": "assistant", "content": bot_msg})
messages.append({"role": "user", "content": message})
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
streamer = TextIteratorStreamer(
tokenizer, skip_prompt=True, skip_special_tokens=True
)
generate_kwargs = dict(
**inputs,
streamer=streamer,
max_new_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
do_sample=True,
)
thread = threading.Thread(target=model.generate, kwargs=generate_kwargs)
thread.start()
response = ""
for new_text in streamer:
response += new_text
yield response
demo = gr.ChatInterface(
fn=respond,
title="Scientific Article Summarizer using BITNet",
description="Copia/pega el texto a resumir de cualquier articulo",
examples=[
[
"Copia todo el texto del articulo cientifico a resumir",
"You are a profesional assistant that summarizes scientific articles.",
512,
0.7,
0.95,
],
],
additional_inputs=[
gr.Textbox(
value="You are a helpful assistant that summarizes scientific articles.",
label="System message"
),
gr.Slider(
minimum=1,
maximum=2048,
value=512,
step=1,
label="Max new tokens"
),
gr.Slider(
minimum=0.1,
maximum=4.0,
value=0.7,
step=0.1,
label="Temperature"
),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)"
),
],
)
if __name__ == "__main__":
demo.launch() |