File size: 4,164 Bytes
5c90aba
 
 
 
 
 
 
1184664
 
 
 
 
 
 
 
 
 
5c90aba
58e4560
 
 
 
 
 
 
 
 
 
5c90aba
58e4560
 
 
 
 
 
5c90aba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58e4560
a1d3e5f
5c90aba
 
 
 
 
 
6531b64
 
 
 
de7122c
 
 
 
 
 
 
 
 
 
5c90aba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f2c5032
5c90aba
 
 
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
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
from huggingface_hub import InferenceClient
import gradio as gr
import random
client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
     
from prompts import GAME_MASTER, COMPRESS_HISTORY
def format_prompt(message, history):
    prompt=""
    '''
    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 compress_history(history,temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
    formatted_prompt=f"{COMPRESS_HISTORY.format(history=history)}"
    generate_kwargs = dict(
        temperature=temperature,
        max_new_tokens=max_new_tokens,
        top_p=top_p,
        repetition_penalty=repetition_penalty,
        do_sample=True,
        seed=random.randint(1,99999999999)
        #seed=42,
    )
    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
    return output

MAX_HISTORY=100

def generate(
    prompt, history, system_prompt, temperature=0.9, 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=random.randint(1,99999999999)
        #seed=42,
    )
    cnt=0
    for ea in history:
        print (ea)
        for l in ea:
            print (l)
            cnt+=len(l.split("\n"))
    print(f'cnt:: {cnt}')
    if cnt > MAX_HISTORY:
        history = compress_history(history, temperature, max_new_tokens, top_p, repetition_penalty)
    formatted_prompt = format_prompt(f"{GAME_MASTER.format(history=history)}, {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

    lines = output.strip().strip("\n").split("\n")
    #history=""
    for i,line in enumerate(lines):
        if line.startswith("1. "):
            print(line)
        if line.startswith("2. "):
            print(line)
        if line.startswith("3. "):
            print(line)
        if line.startswith("4. "):
            print(line)
        if line.startswith("5. "):
            print(line)            
    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=1048,
        minimum=0,
        maximum=1048*10,
        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",
    )
]

examples=[["Start the Game", None, None, None, None, None, ],
          ["Start a Game based in the year 1322", None, None, None, None, None,],
         ]

gr.ChatInterface(
    fn=generate,
    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
    additional_inputs=additional_inputs,
    title="Mixtral RPG Game Master",
    examples=examples,
    concurrency_limit=20,
).launch(share=True,show_api=True)