File size: 7,525 Bytes
8c459b7
 
 
96be83b
 
 
8c459b7
 
96be83b
8c459b7
 
 
 
 
 
 
 
96be83b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8c459b7
96be83b
8c459b7
96be83b
8c459b7
 
 
 
 
 
 
 
 
 
 
 
96be83b
8c459b7
 
 
cc45698
db07d9c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96be83b
 
 
 
 
 
db07d9c
96be83b
db07d9c
 
988491d
96be83b
 
 
db07d9c
96be83b
 
db07d9c
96be83b
 
 
 
 
 
 
 
 
 
 
 
 
 
db07d9c
96be83b
 
 
 
 
 
 
 
db07d9c
96be83b
 
db07d9c
 
96be83b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
db07d9c
96be83b
 
 
 
db07d9c
96be83b
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
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
# import gradio as gr
# from huggingface_hub import InferenceClient

# """
# For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
# """
# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")


# def respond(
#     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": "user", "content": message})

#     response = ""

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

#         response += token
#         yield response

# """
# For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
# """
# demo = gr.ChatInterface(
#     respond,
#     additional_inputs=[
#         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
#         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new 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 (nucleus sampling)",
#         ),
#     ],
# )


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


# import gradio as gr
# from huggingface_hub import InferenceClient

# # Initialize the client with your desired model
# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

# # Format the conversation prompt with history
# def format_prompt(message, history):
#     prompt = "<s>"  # Beginning of sequence for formatting
#     for user_prompt, bot_response in history:
#         prompt += f"[INST] {user_prompt} [/INST]"
#         prompt += f" {bot_response}</s> "
#     prompt += f"[INST] {message} [/INST]"  # Format current user message
#     return prompt

# # Function to generate responses while keeping conversation context
# def generate(
#     prompt, history, 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=42,  # Seed for reproducibility
#     )

#     # Format the prompt with the history and current message
#     formatted_prompt = format_prompt(prompt, history)

#     # Stream the generated response
#     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  # Yield the streamed output as it's generated

# # Customizable input controls for the chatbot interface
# additional_inputs = [
#     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=256,
#         minimum=0,
#         maximum=1048,
#         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",
#     )
# ]

# # Define the chatbot interface with interactive sliders and chatbot panel
# 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="""AI Dermatologist Chatbot"""
# ).launch(show_api=False)

import gradio as gr
from huggingface_hub import InferenceClient

# Initialize the client with your desired model
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

# Define the system prompt as an AI Dermatologist
def format_prompt(message, history):
    prompt = "<s>"
    # Start the conversation with a system message
    prompt += "[INST] You are an AI Dermatologist designed to assist users with skin and hair care.[/INST]"
    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

# Function to generate responses with the AI Dermatologist context
def generate(
    prompt, history, 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=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

# Customizable input controls for the chatbot interface
additional_inputs = [
    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=256,
        minimum=0,
        maximum=1048,
        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",
    )
]

# Define the chatbot interface with the starting system message as AI Dermatologist
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="AI Dermatologist"
).launch(show_api=False)