Commit From AutoTrain
Browse files- .gitattributes +3 -0
- README.md +56 -0
- config.json +61 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +3 -0
- tokenizer_config.json +20 -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 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-classification
|
5 |
+
language:
|
6 |
+
- ar
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain"
|
9 |
+
datasets:
|
10 |
+
- dru-acrps/autotrain-data-dru-text-classification-v2
|
11 |
+
co2_eq_emissions:
|
12 |
+
emissions: 1.5695373677362612
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
- Problem type: Multi-class Classification
|
18 |
+
- Model ID: 85440142814
|
19 |
+
- CO2 Emissions (in grams): 1.5695
|
20 |
+
|
21 |
+
## Validation Metrics
|
22 |
+
|
23 |
+
- Loss: 0.504
|
24 |
+
- Accuracy: 0.853
|
25 |
+
- Macro F1: 0.836
|
26 |
+
- Micro F1: 0.853
|
27 |
+
- Weighted F1: 0.853
|
28 |
+
- Macro Precision: 0.844
|
29 |
+
- Micro Precision: 0.853
|
30 |
+
- Weighted Precision: 0.854
|
31 |
+
- Macro Recall: 0.830
|
32 |
+
- Micro Recall: 0.853
|
33 |
+
- Weighted Recall: 0.853
|
34 |
+
|
35 |
+
|
36 |
+
## Usage
|
37 |
+
|
38 |
+
You can use cURL to access this model:
|
39 |
+
|
40 |
+
```
|
41 |
+
$ 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/dru-acrps/autotrain-dru-text-classification-v2-85440142814
|
42 |
+
```
|
43 |
+
|
44 |
+
Or Python API:
|
45 |
+
|
46 |
+
```
|
47 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
48 |
+
|
49 |
+
model = AutoModelForSequenceClassification.from_pretrained("dru-acrps/autotrain-dru-text-classification-v2-85440142814", use_auth_token=True)
|
50 |
+
|
51 |
+
tokenizer = AutoTokenizer.from_pretrained("dru-acrps/autotrain-dru-text-classification-v2-85440142814", use_auth_token=True)
|
52 |
+
|
53 |
+
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
|
54 |
+
|
55 |
+
outputs = model(**inputs)
|
56 |
+
```
|
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"_num_labels": 14,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "AnthropologyAndSociology",
|
14 |
+
"1": "ArtAndLiterature",
|
15 |
+
"2": "Culture",
|
16 |
+
"3": "Education",
|
17 |
+
"4": "History",
|
18 |
+
"5": "LanguageAndLiguistics",
|
19 |
+
"6": "Law",
|
20 |
+
"7": "Medical",
|
21 |
+
"8": "Philosophy",
|
22 |
+
"9": "Politics",
|
23 |
+
"10": "Religion",
|
24 |
+
"11": "Sports",
|
25 |
+
"12": "finance-and-economy",
|
26 |
+
"13": "science-and-technology"
|
27 |
+
},
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"intermediate_size": 3072,
|
30 |
+
"label2id": {
|
31 |
+
"AnthropologyAndSociology": 0,
|
32 |
+
"ArtAndLiterature": 1,
|
33 |
+
"Culture": 2,
|
34 |
+
"Education": 3,
|
35 |
+
"History": 4,
|
36 |
+
"LanguageAndLiguistics": 5,
|
37 |
+
"Law": 6,
|
38 |
+
"Medical": 7,
|
39 |
+
"Philosophy": 8,
|
40 |
+
"Politics": 9,
|
41 |
+
"Religion": 10,
|
42 |
+
"Sports": 11,
|
43 |
+
"finance-and-economy": 12,
|
44 |
+
"science-and-technology": 13
|
45 |
+
},
|
46 |
+
"layer_norm_eps": 1e-12,
|
47 |
+
"max_length": 64,
|
48 |
+
"max_position_embeddings": 512,
|
49 |
+
"model_type": "bert",
|
50 |
+
"num_attention_heads": 12,
|
51 |
+
"num_hidden_layers": 12,
|
52 |
+
"pad_token_id": 0,
|
53 |
+
"padding": "max_length",
|
54 |
+
"position_embedding_type": "absolute",
|
55 |
+
"problem_type": "single_label_classification",
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.29.2",
|
58 |
+
"type_vocab_size": 2,
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 64000
|
61 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea3f5cdf54c18f8b4b002feb937cf61916db31306189eb93235bf9e6096a5559
|
3 |
+
size 540844176
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2d541447e286f03cb40b8ac969451592ac244b396ee706f51f7392af6233c6a
|
3 |
+
size 540889205
|
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:f47cdf566781758ed5b1f8ae3113d12ab6ac939e912d48adb2a4e98b2cb629c8
|
3 |
+
size 1777125
|
tokenizer_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": false,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"max_len": 512,
|
8 |
+
"model_max_length": 512,
|
9 |
+
"never_split": [
|
10 |
+
"[بريد]",
|
11 |
+
"[مستخدم]",
|
12 |
+
"[رابط]"
|
13 |
+
],
|
14 |
+
"pad_token": "[PAD]",
|
15 |
+
"sep_token": "[SEP]",
|
16 |
+
"strip_accents": null,
|
17 |
+
"tokenize_chinese_chars": true,
|
18 |
+
"tokenizer_class": "BertTokenizer",
|
19 |
+
"unk_token": "[UNK]"
|
20 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|