File size: 2,210 Bytes
743d1bd
0318067
04b933e
0318067
ec89555
1e3869c
1854dfd
0318067
9a692e8
7e5beaf
9c9ed59
0318067
 
 
 
 
 
 
 
 
 
 
 
04b933e
7d03deb
0318067
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
04b933e
 
0318067
 
 
 
 
 
 
 
 
 
 
04b933e
 
0318067
 
 
 
 
 
 
 
 
fb783c6
0318067
fb783c6
0318067
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
from huggingface_hub import InferenceClient

import gradio as gr

import datetime

# Initialize the InferenceClient

client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")

def format_prompt(message, history):

prompt = "<s>"

for user_prompt, bot_response in history:

prompt += f"[INST] {user_prompt} [/INST]"

prompt += f" {bot_response}</s> "

prompt += f"[INST] {message} [/INST]"

return prompt

def generate(prompt, history, system_prompt, temperature=0.9, max_new_tokens=9048, top_p=0.95, repetition_penalty=1.0):

temperature = max(float(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,

)

# Get current time

now = datetime.datetime.now()

formatted_time = now.strftime("%H.%M.%S, %B, %Y")

system_prompt = f"server log: This message was sent at {formatted_time}. The actual year is 2024."

formatted_prompt = format_prompt(f"{system_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

additional_inputs = [

gr.Textbox(label="System Prompt", max_lines=1, interactive=True),

gr.Slider(label="Temperature", value=0.9, minimum=0.0, maximum=1.0, step=0.05, interactive=True, info="Higher values produce more diverse outputs"),

gr.Slider(label="Max new tokens", value=9048, minimum=256, maximum=9048, step=64, interactive=True, info="The maximum numbers of new tokens"),

gr.Slider(label="Top-p (nucleus sampling)", value=0.90, minimum=0.0, maximum=1, step=0.05, interactive=True, info="Higher values sample more low-probability tokens"),

gr.Slider(label="Repetition penalty", value=1.2, minimum=1.0, maximum=2.0, step=0.05, interactive=True, info="Penalize repeated tokens")

]

gr.ChatInterface(

fn=generate,

chatbot=gr.Chatbot(show_label=True, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),

additional_inputs=additional_inputs,

title="ConvoLite",

concurrency_limit=20,

).launch(show_api=False,)