File size: 1,578 Bytes
c022a81
45060c1
c022a81
45060c1
 
 
c022a81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45060c1
c022a81
45060c1
 
 
c022a81
 
45060c1
 
 
 
c022a81
45060c1
c022a81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load model directly
tokenizer = AutoTokenizer.from_pretrained("Leo022/Gemma_QA_For_Telegram_Bot")
model = AutoModelForCausalLM.from_pretrained("Leo022/Gemma_QA_For_Telegram_Bot")

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    input_ids = tokenizer.encode(messages, return_tensors="pt")

    output = model.generate(
        input_ids,
        max_length=max_tokens,
        temperature=temperature,
        top_p=top_p,
        do_sample=True,
    )

    response = tokenizer.decode(output[0], skip_special_tokens=True)

    return response

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", 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()