Commit From AutoTrain
Browse files- .gitattributes +2 -0
- README.md +50 -0
- config.json +37 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +194 -0
- tokenizer_config.json +16 -0
- vocab.txt +30 -0
.gitattributes
CHANGED
@@ -29,3 +29,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
30 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
30 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-classification
|
5 |
+
language:
|
6 |
+
- unk
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain 🤗"
|
9 |
+
datasets:
|
10 |
+
- dav3794/autotrain-data-demo-knots_1_8
|
11 |
+
co2_eq_emissions:
|
12 |
+
emissions: 0.06357782150508624
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
- Problem type: Binary Classification
|
18 |
+
- Model ID: 1316050278
|
19 |
+
- CO2 Emissions (in grams): 0.0636
|
20 |
+
|
21 |
+
## Validation Metrics
|
22 |
+
|
23 |
+
- Loss: 0.242
|
24 |
+
- Accuracy: 0.931
|
25 |
+
- Precision: 0.943
|
26 |
+
- Recall: 0.981
|
27 |
+
- AUC: 0.852
|
28 |
+
- F1: 0.962
|
29 |
+
|
30 |
+
## Usage
|
31 |
+
|
32 |
+
You can use cURL to access this model:
|
33 |
+
|
34 |
+
```
|
35 |
+
$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/dav3794/autotrain-demo-knots_1_8-1316050278
|
36 |
+
```
|
37 |
+
|
38 |
+
Or Python API:
|
39 |
+
|
40 |
+
```
|
41 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
42 |
+
|
43 |
+
model = AutoModelForSequenceClassification.from_pretrained("dav3794/autotrain-demo-knots_1_8-1316050278", use_auth_token=True)
|
44 |
+
|
45 |
+
tokenizer = AutoTokenizer.from_pretrained("dav3794/autotrain-demo-knots_1_8-1316050278", use_auth_token=True)
|
46 |
+
|
47 |
+
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
|
48 |
+
|
49 |
+
outputs = model(**inputs)
|
50 |
+
```
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.0,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"id2label": {
|
13 |
+
"0": "0",
|
14 |
+
"1": "1"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 4096,
|
18 |
+
"label2id": {
|
19 |
+
"0": 0,
|
20 |
+
"1": 1
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-12,
|
23 |
+
"max_length": 256,
|
24 |
+
"max_position_embeddings": 40000,
|
25 |
+
"model_type": "bert",
|
26 |
+
"num_attention_heads": 16,
|
27 |
+
"num_hidden_layers": 30,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"padding": "max_length",
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"problem_type": "single_label_classification",
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.20.0",
|
34 |
+
"type_vocab_size": 2,
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 30
|
37 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1bf64a38d58555ac33d858ffd2e8b7d4a2c247f806a1ab1017df78fdf76359e
|
3 |
+
size 1680217005
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 256,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 256
|
12 |
+
},
|
13 |
+
"direction": "Right",
|
14 |
+
"pad_to_multiple_of": null,
|
15 |
+
"pad_id": 0,
|
16 |
+
"pad_type_id": 0,
|
17 |
+
"pad_token": "[PAD]"
|
18 |
+
},
|
19 |
+
"added_tokens": [
|
20 |
+
{
|
21 |
+
"id": 0,
|
22 |
+
"content": "[PAD]",
|
23 |
+
"single_word": false,
|
24 |
+
"lstrip": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"id": 1,
|
31 |
+
"content": "[UNK]",
|
32 |
+
"single_word": false,
|
33 |
+
"lstrip": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"normalized": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"id": 2,
|
40 |
+
"content": "[CLS]",
|
41 |
+
"single_word": false,
|
42 |
+
"lstrip": false,
|
43 |
+
"rstrip": false,
|
44 |
+
"normalized": false,
|
45 |
+
"special": true
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"id": 3,
|
49 |
+
"content": "[SEP]",
|
50 |
+
"single_word": false,
|
51 |
+
"lstrip": false,
|
52 |
+
"rstrip": false,
|
53 |
+
"normalized": false,
|
54 |
+
"special": true
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"id": 4,
|
58 |
+
"content": "[MASK]",
|
59 |
+
"single_word": false,
|
60 |
+
"lstrip": false,
|
61 |
+
"rstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"special": true
|
64 |
+
}
|
65 |
+
],
|
66 |
+
"normalizer": {
|
67 |
+
"type": "BertNormalizer",
|
68 |
+
"clean_text": true,
|
69 |
+
"handle_chinese_chars": true,
|
70 |
+
"strip_accents": null,
|
71 |
+
"lowercase": false
|
72 |
+
},
|
73 |
+
"pre_tokenizer": {
|
74 |
+
"type": "BertPreTokenizer"
|
75 |
+
},
|
76 |
+
"post_processor": {
|
77 |
+
"type": "TemplateProcessing",
|
78 |
+
"single": [
|
79 |
+
{
|
80 |
+
"SpecialToken": {
|
81 |
+
"id": "[CLS]",
|
82 |
+
"type_id": 0
|
83 |
+
}
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"Sequence": {
|
87 |
+
"id": "A",
|
88 |
+
"type_id": 0
|
89 |
+
}
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"SpecialToken": {
|
93 |
+
"id": "[SEP]",
|
94 |
+
"type_id": 0
|
95 |
+
}
|
96 |
+
}
|
97 |
+
],
|
98 |
+
"pair": [
|
99 |
+
{
|
100 |
+
"SpecialToken": {
|
101 |
+
"id": "[CLS]",
|
102 |
+
"type_id": 0
|
103 |
+
}
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"Sequence": {
|
107 |
+
"id": "A",
|
108 |
+
"type_id": 0
|
109 |
+
}
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"SpecialToken": {
|
113 |
+
"id": "[SEP]",
|
114 |
+
"type_id": 0
|
115 |
+
}
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"Sequence": {
|
119 |
+
"id": "B",
|
120 |
+
"type_id": 1
|
121 |
+
}
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"SpecialToken": {
|
125 |
+
"id": "[SEP]",
|
126 |
+
"type_id": 1
|
127 |
+
}
|
128 |
+
}
|
129 |
+
],
|
130 |
+
"special_tokens": {
|
131 |
+
"[CLS]": {
|
132 |
+
"id": "[CLS]",
|
133 |
+
"ids": [
|
134 |
+
2
|
135 |
+
],
|
136 |
+
"tokens": [
|
137 |
+
"[CLS]"
|
138 |
+
]
|
139 |
+
},
|
140 |
+
"[SEP]": {
|
141 |
+
"id": "[SEP]",
|
142 |
+
"ids": [
|
143 |
+
3
|
144 |
+
],
|
145 |
+
"tokens": [
|
146 |
+
"[SEP]"
|
147 |
+
]
|
148 |
+
}
|
149 |
+
}
|
150 |
+
},
|
151 |
+
"decoder": {
|
152 |
+
"type": "WordPiece",
|
153 |
+
"prefix": "##",
|
154 |
+
"cleanup": true
|
155 |
+
},
|
156 |
+
"model": {
|
157 |
+
"type": "WordPiece",
|
158 |
+
"unk_token": "[UNK]",
|
159 |
+
"continuing_subword_prefix": "##",
|
160 |
+
"max_input_chars_per_word": 100,
|
161 |
+
"vocab": {
|
162 |
+
"[PAD]": 0,
|
163 |
+
"[UNK]": 1,
|
164 |
+
"[CLS]": 2,
|
165 |
+
"[SEP]": 3,
|
166 |
+
"[MASK]": 4,
|
167 |
+
"L": 5,
|
168 |
+
"A": 6,
|
169 |
+
"G": 7,
|
170 |
+
"V": 8,
|
171 |
+
"E": 9,
|
172 |
+
"S": 10,
|
173 |
+
"I": 11,
|
174 |
+
"K": 12,
|
175 |
+
"R": 13,
|
176 |
+
"D": 14,
|
177 |
+
"T": 15,
|
178 |
+
"P": 16,
|
179 |
+
"N": 17,
|
180 |
+
"Q": 18,
|
181 |
+
"F": 19,
|
182 |
+
"Y": 20,
|
183 |
+
"M": 21,
|
184 |
+
"H": 22,
|
185 |
+
"C": 23,
|
186 |
+
"W": 24,
|
187 |
+
"X": 25,
|
188 |
+
"U": 26,
|
189 |
+
"B": 27,
|
190 |
+
"Z": 28,
|
191 |
+
"O": 29
|
192 |
+
}
|
193 |
+
}
|
194 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"full_tokenizer_file": null,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"name_or_path": "AutoTrain",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": null,
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
vocab.txt
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[PAD]
|
2 |
+
[UNK]
|
3 |
+
[CLS]
|
4 |
+
[SEP]
|
5 |
+
[MASK]
|
6 |
+
L
|
7 |
+
A
|
8 |
+
G
|
9 |
+
V
|
10 |
+
E
|
11 |
+
S
|
12 |
+
I
|
13 |
+
K
|
14 |
+
R
|
15 |
+
D
|
16 |
+
T
|
17 |
+
P
|
18 |
+
N
|
19 |
+
Q
|
20 |
+
F
|
21 |
+
Y
|
22 |
+
M
|
23 |
+
H
|
24 |
+
C
|
25 |
+
W
|
26 |
+
X
|
27 |
+
U
|
28 |
+
B
|
29 |
+
Z
|
30 |
+
O
|