File size: 6,426 Bytes
25be583
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""

This script creates an interactive web demo for the GLM-4-9B model using Gradio,

a Python library for building quick and easy UI components for machine learning models.

It's designed to showcase the capabilities of the GLM-4-9B model in a user-friendly interface,

allowing users to interact with the model through a chat-like interface.

"""

import os
import gradio as gr
import torch
from threading import Thread

from typing import Union
from pathlib import Path
from peft import AutoPeftModelForCausalLM, PeftModelForCausalLM
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    PreTrainedModel,
    PreTrainedTokenizer,
    PreTrainedTokenizerFast,
    StoppingCriteria,
    StoppingCriteriaList,
    TextIteratorStreamer
)

DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'

ModelType = Union[PreTrainedModel, PeftModelForCausalLM]
TokenizerType = Union[PreTrainedTokenizer, PreTrainedTokenizerFast]

MODEL_PATH = os.environ.get('MODEL_PATH', '..\models\glm-4-9b-chat')
TOKENIZER_PATH = os.environ.get("TOKENIZER_PATH", MODEL_PATH)


def _resolve_path(path: Union[str, Path]) -> Path:
    return Path(path).expanduser().resolve()


def load_model_and_tokenizer(

        model_dir: Union[str, Path], trust_remote_code: bool = True

) -> tuple[ModelType, TokenizerType]:
    model_dir = _resolve_path(model_dir)
    if (model_dir / 'adapter_config.json').exists():
        model = AutoPeftModelForCausalLM.from_pretrained(
            model_dir, trust_remote_code=trust_remote_code, device_map='auto'
        )
        tokenizer_dir = model.peft_config['default'].base_model_name_or_path
    else:
        model = AutoModelForCausalLM.from_pretrained(
            model_dir, trust_remote_code=trust_remote_code, device_map='auto'
        ).to(DEVICE).eval()
        tokenizer_dir = model_dir
    tokenizer = AutoTokenizer.from_pretrained(
        tokenizer_dir, trust_remote_code=trust_remote_code, use_fast=False
    )
    return model, tokenizer


model, tokenizer = load_model_and_tokenizer(MODEL_PATH, trust_remote_code=True)


class StopOnTokens(StoppingCriteria):
    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
        stop_ids = model.config.eos_token_id
        for stop_id in stop_ids:
            if input_ids[0][-1] == stop_id:
                return True
        return False


def parse_text(text):
    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("<", "&lt;")
                    line = line.replace(">", "&gt;")
                    line = line.replace(" ", "&nbsp;")
                    line = line.replace("*", "&ast;")
                    line = line.replace("_", "&lowbar;")
                    line = line.replace("-", "&#45;")
                    line = line.replace(".", "&#46;")
                    line = line.replace("!", "&#33;")
                    line = line.replace("(", "&#40;")
                    line = line.replace(")", "&#41;")
                    line = line.replace("$", "&#36;")
                lines[i] = "<br>" + line
    text = "".join(lines)
    return text


def predict(history, max_length, top_p, temperature):
    stop = StopOnTokens()
    messages = []
    for idx, (user_msg, model_msg) in enumerate(history):
        if idx == len(history) - 1 and not model_msg:
            messages.append({"role": "user", "content": user_msg})
            break
        if user_msg:
            messages.append({"role": "user", "content": user_msg})
        if model_msg:
            messages.append({"role": "assistant", "content": model_msg})

    model_inputs = tokenizer.apply_chat_template(messages,
                                                 add_generation_prompt=True,
                                                 tokenize=True,
                                                 return_tensors="pt").to(next(model.parameters()).device)
    streamer = TextIteratorStreamer(tokenizer, timeout=60, skip_prompt=True, skip_special_tokens=True)
    generate_kwargs = {
        "input_ids": model_inputs,
        "streamer": streamer,
        "max_new_tokens": max_length,
        "do_sample": True,
        "top_p": top_p,
        "temperature": temperature,
        "stopping_criteria": StoppingCriteriaList([stop]),
        "repetition_penalty": 1.2,
        "eos_token_id": model.config.eos_token_id,
    }
    t = Thread(target=model.generate, kwargs=generate_kwargs)
    t.start()
    for new_token in streamer:
        if new_token:
            history[-1][1] += new_token
        yield history


with gr.Blocks() as demo:
    gr.HTML("""<h1 align="center">GLM-4-9B Gradio Simple Chat Demo</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, container=False)
            with gr.Column(min_width=32, scale=1):
                submitBtn = gr.Button("Submit")
        with gr.Column(scale=1):
            emptyBtn = gr.Button("Clear History")
            max_length = gr.Slider(0, 32768, value=8192, 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(0.01, 1, value=0.6, step=0.01, label="Temperature", interactive=True)


    def user(query, history):
        return "", history + [[parse_text(query), ""]]


    submitBtn.click(user, [user_input, chatbot], [user_input, chatbot], queue=False).then(
        predict, [chatbot, max_length, top_p, temperature], chatbot
    )
    emptyBtn.click(lambda: None, None, chatbot, queue=False)

demo.queue()
demo.launch(server_name="0.0.0.0", server_port=8501, inbrowser=False, share=True)