Spaces:
Sleeping
Sleeping
d1ef
commited on
Commit
·
a1ad15c
1
Parent(s):
bd1449f
add files
Browse files- README.md +4 -5
- app.py +46 -0
- requirements.txt +3 -0
README.md
CHANGED
@@ -1,13 +1,12 @@
|
|
1 |
---
|
2 |
title: Tokenizer Utils
|
3 |
-
emoji:
|
4 |
-
colorFrom:
|
5 |
-
colorTo:
|
6 |
sdk: gradio
|
7 |
-
sdk_version: 3.
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
-
license: mit
|
11 |
---
|
12 |
|
13 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
1 |
---
|
2 |
title: Tokenizer Utils
|
3 |
+
emoji: 🏆
|
4 |
+
colorFrom: blue
|
5 |
+
colorTo: blue
|
6 |
sdk: gradio
|
7 |
+
sdk_version: 3.48.0
|
8 |
app_file: app.py
|
9 |
pinned: false
|
|
|
10 |
---
|
11 |
|
12 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
app.py
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
from transformers import T5Tokenizer
|
3 |
+
import json
|
4 |
+
|
5 |
+
ACTIONS = ["text2ids", "text2tokens", "ids2tokens", "tokens2ids and JSON requires double quotes"]
|
6 |
+
|
7 |
+
def translate(model, action, inputs):
|
8 |
+
tokenizer = T5Tokenizer.from_pretrained(model)
|
9 |
+
vocab_size = tokenizer.vocab_size
|
10 |
+
len_tokenizer = len(tokenizer)
|
11 |
+
input = inputs
|
12 |
+
output = ''
|
13 |
+
if action == ACTIONS[0]:
|
14 |
+
input_ids = tokenizer(input)['input_ids']
|
15 |
+
output = input_ids
|
16 |
+
|
17 |
+
if action == ACTIONS[1]:
|
18 |
+
input_ids = tokenizer(input)['input_ids']
|
19 |
+
tokens = tokenizer.convert_ids_to_tokens(input_ids)
|
20 |
+
output = tokens
|
21 |
+
if action == ACTIONS[2]:
|
22 |
+
list = json.loads(input)
|
23 |
+
tokens = tokenizer.convert_ids_to_tokens(list)
|
24 |
+
output = tokens
|
25 |
+
if action == ACTIONS[3]:
|
26 |
+
list = json.loads(input)
|
27 |
+
tokens = tokenizer.convert_tokens_to_ids(list)
|
28 |
+
output = tokens
|
29 |
+
|
30 |
+
|
31 |
+
return f'{output}\n\n\n\nother infos:\nvocab_size: {vocab_size}\nlen(tokenizer): {len_tokenizer}'
|
32 |
+
|
33 |
+
demo = gr.Interface(
|
34 |
+
fn=translate,
|
35 |
+
inputs=[
|
36 |
+
gr.components.Textbox(label="MODEL NAME, eg: t5-small"),
|
37 |
+
gr.components.Dropdown(label="ACTIONS", choices=ACTIONS),
|
38 |
+
gr.components.Textbox(label="INPUTS"),
|
39 |
+
],
|
40 |
+
outputs=["text"],
|
41 |
+
cache_examples=False,
|
42 |
+
title="Test T5Tokenizer",
|
43 |
+
description="▁Test, ▁To, ken, izer, s, ▁happily, !, </s>"
|
44 |
+
)
|
45 |
+
|
46 |
+
demo.launch(debug=True)
|
requirements.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
transformers==4.34.0
|
2 |
+
sentencepiece==0.1.99
|
3 |
+
numpy==1.24.2
|