File size: 6,081 Bytes
b31a023 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 |
import argparse
import os
import warnings
import mdtex2html
import gradio as gr
import re
pattern = re.compile("[\n]+")
import torch
from accelerate import init_empty_weights, load_checkpoint_and_dispatch
from huggingface_hub import snapshot_download
from transformers.generation.utils import logger
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
parser = argparse.ArgumentParser()
parser.add_argument("--model_name", default="DAMO-NLP-MT/polylm-multialpaca-13b",
choices=["DAMO-NLP-MT/polylm-multialpaca-13b"], type=str)
parser.add_argument("--gpu", default="0", type=str)
args = parser.parse_args()
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
num_gpus = len(args.gpu.split(","))
if ('int8' in args.model_name or 'int4' in args.model_name) and num_gpus > 1:
raise ValueError("Quantized models do not support model parallel. Please run on a single GPU (e.g., --gpu 0).")
logger.setLevel("ERROR")
warnings.filterwarnings("ignore")
model_path = args.model_name
if not os.path.exists(args.model_name):
model_path = snapshot_download(args.model_name)
config = AutoConfig.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False)
if num_gpus > 1:
print("Waiting for all devices to be ready, it may take a few minutes...")
with init_empty_weights():
raw_model = AutoModelForCausalLM.from_config(config)
raw_model.tie_weights()
model = load_checkpoint_and_dispatch(
raw_model, model_path, device_map="auto", no_split_module_classes=["GPT2Block"]
)
else:
print("Loading model files, it may take a few minutes...")
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True).cuda()
def postprocess(self, y):
if y is None:
return []
for i, (message, response) in enumerate(y):
y[i] = (
None if message is None else mdtex2html.convert((message)),
None if response is None else mdtex2html.convert(response),
)
return y
gr.Chatbot.postprocess = postprocess
def parse_text(text):
"""copy from https://github.com/GaiZhenbiao/ChuanhuChatGPT/"""
lines = text.split("\n")
lines = [line for line in lines if line != ""]
count = 0
for i, line in enumerate(lines):
if "```" in line:
count += 1
items = line.split('`')
if count % 2 == 1:
lines[i] = f'<pre><code class="language-{items[-1]}">'
else:
lines[i] = f'<br></code></pre>'
else:
if i > 0:
if count % 2 == 1:
line = line.replace("`", "\`")
line = line.replace("<", "<")
line = line.replace(">", ">")
line = line.replace(" ", " ")
line = line.replace("*", "*")
line = line.replace("_", "_")
line = line.replace("-", "-")
line = line.replace(".", ".")
line = line.replace("!", "!")
line = line.replace("(", "(")
line = line.replace(")", ")")
line = line.replace("$", "$")
lines[i] = "<br>"+line
text = "".join(lines)
return text
def predict(input, chatbot, max_length, top_p, temperature, history):
query = input
query = query.strip()
query = re.sub(pattern, "\n", query)
chatbot.append((query, ""))
prompt = ""
for i, (old_query, response) in enumerate(history):
prompt += f"{old_query}\n\n" + f"{response}\n"
prompt += f"{query}\n\n"
inputs = tokenizer(prompt, return_tensors="pt")
with torch.no_grad():
outputs = model.generate(
inputs.input_ids.cuda(),
attention_mask=inputs.attention_mask.cuda(),
max_length=max_length,
do_sample=True,
top_p=top_p,
temperature=temperature,
repetition_penalty=1.02,
num_return_sequences=1,
eos_token_id=2,
early_stopping=True)
response = tokenizer.decode(
outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
chatbot[-1] = (query, parse_text(response))
history = history + [(query, response)]
print("==========================================================================")
print(f"chatbot is {chatbot}")
print(f"history is {history}")
print("==========================================================================")
return chatbot, history
def reset_user_input():
return gr.update(value='')
def reset_state():
return [], []
with gr.Blocks() as demo:
gr.HTML("""<h1 align="center">欢迎使用 PolyLM 多语言人工智能助手！</h1>""")
chatbot = gr.Chatbot()
with gr.Row():
with gr.Column(scale=4):
with gr.Column(scale=12):
user_input = gr.Textbox(show_label=False, placeholder="Input...", lines=10).style(
container=False)
with gr.Column(min_width=32, scale=1):
submitBtn = gr.Button("Submit", variant="primary")
with gr.Column(scale=1):
emptyBtn = gr.Button("Clear History")
max_length = gr.Slider(
0, 4096, value=2048, step=1.0, label="Maximum length", interactive=True)
top_p = gr.Slider(0, 1, value=0.8, step=0.01,
label="Top P", interactive=True)
temperature = gr.Slider(
0, 1, value=0.7, step=0.01, label="Temperature", interactive=True)
history = gr.State([]) # (message, bot_message)
submitBtn.click(predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history],
show_progress=True)
submitBtn.click(reset_user_input, [], [user_input])
emptyBtn.click(reset_state, outputs=[chatbot, history], show_progress=True)
demo.queue().launch(share=False, inbrowser=True)
|