Commit From AutoTrain
Browse files- .gitattributes +3 -0
- README.md +50 -0
- config.json +43 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +3 -0
- tokenizer_config.json +49 -0
- vocab.txt +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
37 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
38 |
+
tokenizer.json 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 |
+
- Anwaarma/autotrain-data-enhancedauto
|
11 |
+
co2_eq_emissions:
|
12 |
+
emissions: 3.3106524610859784
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
- Problem type: Binary Classification
|
18 |
+
- Model ID: 72049138835
|
19 |
+
- CO2 Emissions (in grams): 3.3107
|
20 |
+
|
21 |
+
## Validation Metrics
|
22 |
+
|
23 |
+
- Loss: 0.042
|
24 |
+
- Accuracy: 0.990
|
25 |
+
- Precision: 0.994
|
26 |
+
- Recall: 0.935
|
27 |
+
- AUC: 0.997
|
28 |
+
- F1: 0.964
|
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/Anwaarma/autotrain-enhancedauto-72049138835
|
36 |
+
```
|
37 |
+
|
38 |
+
Or Python API:
|
39 |
+
|
40 |
+
```
|
41 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
42 |
+
|
43 |
+
model = AutoModelForSequenceClassification.from_pretrained("Anwaarma/autotrain-enhancedauto-72049138835", use_auth_token=True)
|
44 |
+
|
45 |
+
tokenizer = AutoTokenizer.from_pretrained("Anwaarma/autotrain-enhancedauto-72049138835", 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 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "0",
|
15 |
+
"1": "1"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"0": 0,
|
21 |
+
"1": 1
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"max_length": 192,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "bert",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"padding": "max_length",
|
31 |
+
"pooler_fc_size": 768,
|
32 |
+
"pooler_num_attention_heads": 12,
|
33 |
+
"pooler_num_fc_layers": 3,
|
34 |
+
"pooler_size_per_head": 128,
|
35 |
+
"pooler_type": "first_token_transform",
|
36 |
+
"position_embedding_type": "absolute",
|
37 |
+
"problem_type": "single_label_classification",
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.29.2",
|
40 |
+
"type_vocab_size": 2,
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 64000
|
43 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41eb64b01d5f7a9e632f6c47405222e1916dd8f201abcbbc311797cc7d628f23
|
3 |
+
size 540807264
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b56a9a7f45662517a5cc2b42e4e725522e4ac1e9a5f7cc9b3cedc9a2070f683
|
3 |
+
size 540852341
|
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 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75ab275053dcac1679196a4293cadd09be0151ab95f0dba80f74e09d1280040d
|
3 |
+
size 1674480
|
tokenizer_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": false,
|
6 |
+
"full_tokenizer_file": null,
|
7 |
+
"mask_token": "[MASK]",
|
8 |
+
"max_len": 512,
|
9 |
+
"model_max_length": 512,
|
10 |
+
"never_split": [
|
11 |
+
"+وا",
|
12 |
+
"س+",
|
13 |
+
"[مستخدم]",
|
14 |
+
"+ك",
|
15 |
+
"+هم",
|
16 |
+
"+ة",
|
17 |
+
"+ن",
|
18 |
+
"لل+",
|
19 |
+
"[بريد]",
|
20 |
+
"[رابط]",
|
21 |
+
"+ه",
|
22 |
+
"+كن",
|
23 |
+
"+ا",
|
24 |
+
"+ات",
|
25 |
+
"+ي",
|
26 |
+
"ب+",
|
27 |
+
"+نا",
|
28 |
+
"+هن",
|
29 |
+
"+كم",
|
30 |
+
"ك+",
|
31 |
+
"+ين",
|
32 |
+
"+هما",
|
33 |
+
"و+",
|
34 |
+
"+كما",
|
35 |
+
"+ان",
|
36 |
+
"+ت",
|
37 |
+
"+ون",
|
38 |
+
"ل+",
|
39 |
+
"+ها",
|
40 |
+
"ال+",
|
41 |
+
"ف+"
|
42 |
+
],
|
43 |
+
"pad_token": "[PAD]",
|
44 |
+
"sep_token": "[SEP]",
|
45 |
+
"strip_accents": null,
|
46 |
+
"tokenize_chinese_chars": true,
|
47 |
+
"tokenizer_class": "BertTokenizer",
|
48 |
+
"unk_token": "[UNK]"
|
49 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|