File size: 1,188 Bytes
d3d1e52
69a8ba9
d3d1e52
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69a8ba9
2d66e4d
d3d1e52
 
 
 
 
 
 
 
471735c
d3d1e52
 
 
 
3706199
d3d1e52
 
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
from huggingface_hub import InferenceClient
import gradio as gr

client = InferenceClient()

def respond(
    prompt: str,
    history,
):
    if not history:
        history = [{"role": "system", "content": "You are a friendly chatbot"}]
    history.append({"role": "user", "content": prompt})

    yield history

    response = {"role": "assistant", "content": ""}
    for message in client.chat_completion(
        history,
        temperature=0.95,
        top_p=0.9,
        max_tokens=512,
        stream=True,
        model="HuggingFaceH4/zephyr-7b-beta"
    ):
        response["content"] += message.choices[0].delta.content or ""

        yield history + [response]


with gr.Blocks() as demo:
    gr.Markdown("# Chat with Hugging Face Zephyr 7b 🤗")
    chatbot = gr.Chatbot(
        label="Agent",
        type="messages",
        avatar_images=(
            None,
            "https://em-content.zobj.net/source/twitter/376/hugging-face_1f917.png",
        ),
    )
    prompt = gr.Textbox(max_lines=1, label="Chat Message")
    prompt.submit(respond, [prompt, chatbot], [chatbot])
    prompt.submit(lambda: "", None, [prompt])


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