File size: 4,818 Bytes
da90805
 
1ad806d
da90805
 
 
 
1ad806d
da90805
 
 
 
 
 
 
 
 
 
 
 
1ad806d
 
da90805
 
 
 
 
 
1ad806d
 
da90805
 
 
 
 
1ad806d
da90805
 
 
 
 
 
 
1ad806d
da90805
 
 
 
1ad806d
da90805
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1ad806d
da90805
 
 
1ad806d
da90805
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1ad806d
da90805
 
 
 
 
1ad806d
da90805
4e3e7a7
1ad806d
da90805
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1ad806d
 
da90805
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
# Ref: https://huggingface.co/spaces/ysharma/Chat_with_Meta_llama3_8b

import gradio as gr
import spaces
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
from threading import Thread

DESCRIPTION = '''
<div>
<h1 style="text-align: center;">Sarashina2.2-3B Instruct</h1>
<p>非公式Sarashina2.2-3B Instructだよ。 <a href="https://huggingface.co/sbintuitions/sarashina2.2-3b-instruct-v0.1"><b>sbintuitions/sarashina2.2-3b-instruct-v0.1</b></a>.</p>
</div>
'''

LICENSE = """
<p/>

---
Built with Sarashina
"""

PLACEHOLDER = """
<div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">非公式 Sarashina2.2-3B Instruct Test</h1>
   <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">なんでもきいてね</p>
</div>
"""


css = """
h1 {
  text-align: center;
  display: block;
}

#duplicate-button {
  margin: auto;
  color: white;
  background: #1565c0;
  border-radius: 100vh;
}
"""

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("sbintuitions/sarashina2.2-3b-instruct-v0.1", use_fast=False)
model = AutoModelForCausalLM.from_pretrained("sbintuitions/sarashina2.2-3b-instruct-v0.1", torch_dtype=torch.bfloat16)
model=model.to("cuda:0")

@spaces.GPU()
def chat_llama3_8b(message: str, 
              history: list, 
              temperature: float, 
              max_new_tokens: int
             ) -> str:
    """
    Generate a streaming response using the llama3-8b model.
    Args:
        message (str): The input message.
        history (list): The conversation history used by ChatInterface.
        temperature (float): The temperature for generating the response.
        max_new_tokens (int): The maximum number of new tokens to generate.
    Returns:
        str: The generated response.
    """
    conversation = []
    for user, assistant in history:
        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
    conversation.append({"role": "user", "content": message})

    input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True,return_tensors="pt")
    
    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)

    generate_kwargs = dict(
        input_ids= input_ids.to(model.device),
        streamer=streamer,
        max_new_tokens=max_new_tokens,
        do_sample=True,
        temperature=temperature,
        top_p=0.95,
        repetition_penalty=1.1,
    )
    # This will enforce greedy generation (do_sample=False) when the temperature is passed 0, avoiding the crash.             
    if temperature == 0:
        generate_kwargs['do_sample'] = False
        
    t = Thread(target=model.generate, kwargs=generate_kwargs)
    t.start()

    outputs = []
    for text in streamer:
        outputs.append(text)
        yield "".join(outputs)
        

# Gradio block
chatbot=gr.Chatbot(height=450, placeholder=PLACEHOLDER, label='Gradio ChatInterface', scale=1)

with gr.Blocks(fill_height=True, css=css) as demo:
    
    gr.Markdown(DESCRIPTION)
    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
    gr.ChatInterface(
        fn=chat_llama3_8b,
        chatbot=chatbot,
        fill_height=True,
        additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
        additional_inputs=[
            gr.Slider(minimum=0,
                      maximum=1, 
                      step=0.1,
                      value=0.5, 
                      label="Temperature", 
                      render=False),
            gr.Slider(minimum=128, 
                      maximum=4096,
                      step=1,
                      value=512, 
                      label="Max new tokens", 
                      render=False ),
            ],
        examples=[
            ['小学生にもわかるように相対性理論を教えてください。'],
            ['宇宙の起源を知るための方法をステップ・バイ・ステップで教えてください。'],
            ['1から100までの素数を求めるスクリプトをPythonで書いてください。'],
            ['友達の陽葵にあげる誕生日プレゼントを考えてください。ただし、陽葵は中学生で、私は同じクラスの男性であることを考慮してください。'],
            ['ペンギンがジャングルの王様であることを正当化するように説明してください。']
            ],
        cache_examples=False,
                     )
    
    gr.Markdown(LICENSE)
    
if __name__ == "__main__":
    demo.launch()