File size: 1,500 Bytes
ba0918e
 
 
a45f57c
ba0918e
 
89d1b8c
ba0918e
 
 
 
 
 
 
df5a2a4
ba0918e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8481591
ba0918e
 
 
69f75d6
ba0918e
 
19423df
ba0918e
9ecd148
ba0918e
6f52537
ba0918e
 
19423df
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
from huggingface_hub import InferenceClient
import gradio as gr

client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

def format_prompt(message, history):
  prompt = "<|system|>\n</s>\n"
  for user_prompt, bot_response in history:
    prompt += f"<|user|>\n {user_prompt} </s>\n"
    prompt += f"<|assistant|>\n {bot_response} \n</s>\n "
  prompt += f"<|user|>\n {message} </s>\n<|assistant|>"
  return prompt

def generate(
    prompt, history, temperature=0.1, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
):
    temperature = float(temperature)
    if temperature < 1e-2:
        temperature = 1e-2
    top_p = float(top_p)

    generate_kwargs = dict(
        temperature=temperature,
        max_new_tokens=max_new_tokens,
        top_p=top_p,
        repetition_penalty=repetition_penalty,
        do_sample=True,
        seed=42,
    )

    formatted_prompt = format_prompt(prompt, history)

    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
    output = ""

    for response in stream:
        output += response.token.text
        yield output
    # return output


mychatbot = gr.Chatbot(
    avatar_images=["./user.png", "./botz.png"], bubble_full_width=False, show_label=False, show_copy_button=True,)


demo = gr.ChatInterface(fn=generate, 
        chatbot=mychatbot,
        title="Tomoniai Zephyr 7b Chat",
        retry_btn=None,
        undo_btn=None
    )

demo.queue().launch(show_api=False)