File size: 1,982 Bytes
4ab8c75
 
dfddde4
de1b844
 
68d1aeb
de1b844
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dfddde4
de1b844
 
 
0d4f546
de1b844
 
 
 
 
 
 
 
 
 
 
 
4ab8c75
 
 
 
 
e10e33e
4ab8c75
 
 
 
1156050
4ab8c75
 
 
 
 
 
 
ce2aedb
c50b40a
4ab8c75
 
 
224f79a
 
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
# Inference

import gradio as gr
from huggingface_hub import InferenceClient

model = "meta-llama/Llama-3.2-3B-Instruct"
client = InferenceClient(model)

def fn(
    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": "bot", "content": val[1]})

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

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens = max_tokens,
        temperature = temperature,
        top_p = top_p,
        stream = True,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response

app = gr.ChatInterface(
    fn = fn,
    additional_inputs = [
        gr.Textbox(value="You are a helpful assistant.", label="System Message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max 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"),
    ],
    title = "Meta Llama",
    description = model,
)

if __name__ == "__main__":
    app.launch()

"""
# Pipeline

import gradio as gr
from transformers import pipeline

pipe = pipeline(model = "meta-llama/Llama-3.2-3B-Instruct")

def fn(input):
    output = pipe(
        input,
        max_new_tokens = 2048
    )
    return output[0]["generated_text"]#[len(input):]

app = gr.Interface(
    fn = fn,
    inputs = [gr.Textbox(label = "Input")],
    outputs = [gr.Textbox(label = "Output")],
    title = "Meta Llama",
    description = "Pipeline",
    examples = [
        ["Hello, World."]
    ]
).launch()
"""