Bhaskar2611 commited on
Commit
e675232
·
verified ·
1 Parent(s): 243d4ef

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +146 -53
app.py CHANGED
@@ -1,64 +1,157 @@
1
- import gradio as gr
2
- from huggingface_hub import InferenceClient
3
 
4
- """
5
- 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
6
- """
7
- client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
8
 
9
 
10
- def respond(
11
- message,
12
- history: list[tuple[str, str]],
13
- system_message,
14
- max_tokens,
15
- temperature,
16
- top_p,
17
- ):
18
- messages = [{"role": "system", "content": system_message}]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
 
20
- for val in history:
21
- if val[0]:
22
- messages.append({"role": "user", "content": val[0]})
23
- if val[1]:
24
- messages.append({"role": "assistant", "content": val[1]})
25
 
26
- messages.append({"role": "user", "content": message})
27
 
28
- response = ""
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
 
30
- for message in client.chat_completion(
31
- messages,
32
- max_tokens=max_tokens,
33
- stream=True,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  temperature=temperature,
 
35
  top_p=top_p,
36
- ):
37
- token = message.choices[0].delta.content
38
-
39
- response += token
40
- yield response
41
-
42
-
43
- """
44
- For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
45
- """
46
- demo = gr.ChatInterface(
47
- respond,
48
- additional_inputs=[
49
- gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
50
- gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
51
- gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
52
- gr.Slider(
53
- minimum=0.1,
54
- maximum=1.0,
55
- value=0.95,
56
- step=0.05,
57
- label="Top-p (nucleus sampling)",
58
- ),
59
- ],
60
- )
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
 
62
 
63
- if __name__ == "__main__":
64
- demo.launch()
 
1
+ # import gradio as gr
2
+ # from huggingface_hub import InferenceClient
3
 
4
+ # """
5
+ # 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
6
+ # """
7
+ # client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
8
 
9
 
10
+ # def respond(
11
+ # message,
12
+ # history: list[tuple[str, str]],
13
+ # system_message,
14
+ # max_tokens,
15
+ # temperature,
16
+ # top_p,
17
+ # ):
18
+ # messages = [{"role": "system", "content": system_message}]
19
+
20
+ # for val in history:
21
+ # if val[0]:
22
+ # messages.append({"role": "user", "content": val[0]})
23
+ # if val[1]:
24
+ # messages.append({"role": "assistant", "content": val[1]})
25
+
26
+ # messages.append({"role": "user", "content": message})
27
+
28
+ # response = ""
29
+
30
+ # for message in client.chat_completion(
31
+ # messages,
32
+ # max_tokens=max_tokens,
33
+ # stream=True,
34
+ # temperature=temperature,
35
+ # top_p=top_p,
36
+ # ):
37
+ # token = message.choices[0].delta.content
38
 
39
+ # response += token
40
+ # yield response
 
 
 
41
 
 
42
 
43
+ # """
44
+ # For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
45
+ # """
46
+ # demo = gr.ChatInterface(
47
+ # respond,
48
+ # additional_inputs=[
49
+ # gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
50
+ # gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
51
+ # gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
52
+ # gr.Slider(
53
+ # minimum=0.1,
54
+ # maximum=1.0,
55
+ # value=0.95,
56
+ # step=0.05,
57
+ # label="Top-p (nucleus sampling)",
58
+ # ),
59
+ # ],
60
+ # )
61
+
62
+
63
+ # if __name__ == "__main__":
64
+ # demo.launch()
65
+ from huggingface_hub import InferenceClient
66
+ import gradio as gr
67
+
68
+ client = InferenceClient(
69
+ "mistralai/Mistral-7B-Instruct-v0.3"
70
+ )
71
 
72
+
73
+ def format_prompt(message, history):
74
+ prompt = "<s>"
75
+ for user_prompt, bot_response in history:
76
+ prompt += f"[INST] {user_prompt} [/INST]"
77
+ prompt += f" {bot_response}</s> "
78
+ prompt += f"[INST] {message} [/INST]"
79
+ return prompt
80
+
81
+ def generate(
82
+ prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
83
+ ):
84
+ temperature = float(temperature)
85
+ if temperature < 1e-2:
86
+ temperature = 1e-2
87
+ top_p = float(top_p)
88
+
89
+ generate_kwargs = dict(
90
  temperature=temperature,
91
+ max_new_tokens=max_new_tokens,
92
  top_p=top_p,
93
+ repetition_penalty=repetition_penalty,
94
+ do_sample=True,
95
+ seed=42,
96
+ )
97
+
98
+ formatted_prompt = format_prompt(prompt, history)
99
+
100
+ stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
101
+ output = ""
102
+
103
+ for response in stream:
104
+ output += response.token.text
105
+ yield output
106
+ return output
107
+
108
+
109
+ additional_inputs=[
110
+ gr.Slider(
111
+ label="Temperature",
112
+ value=0.9,
113
+ minimum=0.0,
114
+ maximum=1.0,
115
+ step=0.05,
116
+ interactive=True,
117
+ info="Higher values produce more diverse outputs",
118
+ ),
119
+ gr.Slider(
120
+ label="Max new tokens",
121
+ value=256,
122
+ minimum=0,
123
+ maximum=1048,
124
+ step=64,
125
+ interactive=True,
126
+ info="The maximum numbers of new tokens",
127
+ ),
128
+ gr.Slider(
129
+ label="Top-p (nucleus sampling)",
130
+ value=0.90,
131
+ minimum=0.0,
132
+ maximum=1,
133
+ step=0.05,
134
+ interactive=True,
135
+ info="Higher values sample more low-probability tokens",
136
+ ),
137
+ gr.Slider(
138
+ label="Repetition penalty",
139
+ value=1.2,
140
+ minimum=1.0,
141
+ maximum=2.0,
142
+ step=0.05,
143
+ interactive=True,
144
+ info="Penalize repeated tokens",
145
+ )
146
+ ]
147
+
148
+
149
+ gr.ChatInterface(
150
+ fn=generate,
151
+ chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
152
+ additional_inputs=additional_inputs,
153
+ title="""AI Dermatologist"""
154
+ ).launch(show_api=False)
155
 
156
 
157
+ gr.load("models/Bhaskar2611/Capstone").launch()