Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -1,60 +1,43 @@
|
|
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 |
-
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
|
44 |
-
"""
|
45 |
demo = gr.ChatInterface(
|
46 |
respond,
|
47 |
additional_inputs=[
|
48 |
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
|
49 |
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
|
50 |
-
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
|
51 |
-
gr.Slider(
|
52 |
-
minimum=0.1,
|
53 |
-
maximum=1.0,
|
54 |
-
value=0.95,
|
55 |
-
step=0.05,
|
56 |
-
label="Top-p (nucleus sampling)",
|
57 |
-
),
|
58 |
],
|
59 |
)
|
60 |
|
|
|
1 |
import gradio as gr
|
2 |
from huggingface_hub import InferenceClient
|
3 |
+
import numpy as np
|
4 |
+
import pandas as pd
|
5 |
+
from transformers import pipeline
|
6 |
+
import torch
|
7 |
+
|
8 |
+
model = "meta-llama/Meta-Llama-3-8B"
|
9 |
+
generator=pipeline(task='text-generation', model=model)
|
10 |
+
|
11 |
+
|
12 |
+
tones = {
|
13 |
+
'natural': 'human, authentic',
|
14 |
+
'fluency': 'readable, clarified',
|
15 |
+
'formal': 'sophistocated',
|
16 |
+
'academic': 'technical and scholarly',
|
17 |
+
'simple': 'simple and easily understandable',
|
18 |
+
}
|
19 |
+
|
20 |
+
|
21 |
+
def generate(text, max_length):
|
22 |
+
x=generator(text, max_length=max_length, num_return_sequences=1)
|
23 |
+
return x
|
24 |
+
|
25 |
+
|
26 |
+
def respond(message, tone="natural", max_length=512):
|
27 |
+
prompt = f"Paraphrase this text in a more {tones[tone]} way: {message}"
|
28 |
+
text = generate(prompt, max_length)
|
29 |
+
print(text)
|
30 |
+
text = text[0]["generated_text"]
|
31 |
+
if prompt in text:
|
32 |
+
text = text.split(":", 1)[1]
|
33 |
+
return text
|
34 |
+
|
35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
demo = gr.ChatInterface(
|
37 |
respond,
|
38 |
additional_inputs=[
|
39 |
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
|
40 |
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
41 |
],
|
42 |
)
|
43 |
|