Commit From AutoTrain
Browse files- .gitattributes +2 -0
- README.md +52 -0
- config.json +43 -0
- pytorch_model.bin +3 -0
- sample_input.pkl +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
.gitattributes
CHANGED
@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags: autotrain
|
3 |
+
language: unk
|
4 |
+
widget:
|
5 |
+
- text: "I love AutoTrain 🤗"
|
6 |
+
datasets:
|
7 |
+
- ikram54/autotrain-data-harassement
|
8 |
+
co2_eq_emissions: 2.6332836871905054
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Trained Using AutoTrain
|
12 |
+
|
13 |
+
- Problem type: Multi-class Classification
|
14 |
+
- Model ID: 675420038
|
15 |
+
- CO2 Emissions (in grams): 2.6332836871905054
|
16 |
+
|
17 |
+
## Validation Metrics
|
18 |
+
|
19 |
+
- Loss: 0.8747465014457703
|
20 |
+
- Accuracy: 0.7085201793721974
|
21 |
+
- Macro F1: 0.579743989078862
|
22 |
+
- Micro F1: 0.7085201793721974
|
23 |
+
- Weighted F1: 0.6913786522271296
|
24 |
+
- Macro Precision: 0.5669375905888698
|
25 |
+
- Micro Precision: 0.7085201793721974
|
26 |
+
- Weighted Precision: 0.6760144007300164
|
27 |
+
- Macro Recall: 0.5940655209452201
|
28 |
+
- Micro Recall: 0.7085201793721974
|
29 |
+
- Weighted Recall: 0.7085201793721974
|
30 |
+
|
31 |
+
|
32 |
+
## Usage
|
33 |
+
|
34 |
+
You can use cURL to access this model:
|
35 |
+
|
36 |
+
```
|
37 |
+
$ 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/ikram54/autotrain-harassement-675420038
|
38 |
+
```
|
39 |
+
|
40 |
+
Or Python API:
|
41 |
+
|
42 |
+
```
|
43 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
44 |
+
|
45 |
+
model = AutoModelForSequenceClassification.from_pretrained("ikram54/autotrain-harassement-675420038", use_auth_token=True)
|
46 |
+
|
47 |
+
tokenizer = AutoTokenizer.from_pretrained("ikram54/autotrain-harassement-675420038", use_auth_token=True)
|
48 |
+
|
49 |
+
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
|
50 |
+
|
51 |
+
outputs = model(**inputs)
|
52 |
+
```
|
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"_num_labels": 5,
|
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": "Indirect Harassment",
|
14 |
+
"1": "Not Hate",
|
15 |
+
"2": "Not Sexist",
|
16 |
+
"3": "Physical Harassment",
|
17 |
+
"4": "Sexual Harassment"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"Indirect Harassment": 0,
|
23 |
+
"Not Hate": 1,
|
24 |
+
"Not Sexist": 2,
|
25 |
+
"Physical Harassment": 3,
|
26 |
+
"Sexual Harassment": 4
|
27 |
+
},
|
28 |
+
"layer_norm_eps": 1e-12,
|
29 |
+
"max_length": 256,
|
30 |
+
"max_position_embeddings": 512,
|
31 |
+
"model_type": "bert",
|
32 |
+
"num_attention_heads": 12,
|
33 |
+
"num_hidden_layers": 12,
|
34 |
+
"pad_token_id": 0,
|
35 |
+
"padding": "max_length",
|
36 |
+
"position_embedding_type": "absolute",
|
37 |
+
"problem_type": "single_label_classification",
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.15.0",
|
40 |
+
"type_vocab_size": 2,
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 64000
|
43 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:849a15fdea59c03687dfe4cc098c97af4d26108b5ff258445287cf99223a7522
|
3 |
+
size 540872877
|
sample_input.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09cfd94657d7cff948d572f6dd2194449f293f67f2e166146c0543b3925fd8d7
|
3 |
+
size 7462
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "do_basic_tokenize": true, "never_split": ["[بريد]", "[مستخدم]", "[رابط]"], "special_tokens_map_file": null, "name_or_path": "AutoTrain", "tokenizer_class": "BertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|