Commit From AutoNLP
Browse files- .gitattributes +2 -0
- README.md +52 -0
- config.json +78 -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: autonlp
|
3 |
+
language: en
|
4 |
+
widget:
|
5 |
+
- text: "I love AutoNLP 🤗"
|
6 |
+
datasets:
|
7 |
+
- Chijioke/autonlp-data-mono
|
8 |
+
co2_eq_emissions: 1.1406456838043837
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Trained Using AutoNLP
|
12 |
+
|
13 |
+
- Problem type: Multi-class Classification
|
14 |
+
- Model ID: 625317956
|
15 |
+
- CO2 Emissions (in grams): 1.1406456838043837
|
16 |
+
|
17 |
+
## Validation Metrics
|
18 |
+
|
19 |
+
- Loss: 0.513037919998169
|
20 |
+
- Accuracy: 0.8982035928143712
|
21 |
+
- Macro F1: 0.7843756230226546
|
22 |
+
- Micro F1: 0.8982035928143712
|
23 |
+
- Weighted F1: 0.8891653474608059
|
24 |
+
- Macro Precision: 0.8210878091622635
|
25 |
+
- Micro Precision: 0.8982035928143712
|
26 |
+
- Weighted Precision: 0.8888857327766032
|
27 |
+
- Macro Recall: 0.7731018645485747
|
28 |
+
- Micro Recall: 0.8982035928143712
|
29 |
+
- Weighted Recall: 0.8982035928143712
|
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 AutoNLP"}' https://api-inference.huggingface.co/models/Chijioke/autonlp-mono-625317956
|
38 |
+
```
|
39 |
+
|
40 |
+
Or Python API:
|
41 |
+
|
42 |
+
```
|
43 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
44 |
+
|
45 |
+
model = AutoModelForSequenceClassification.from_pretrained("Chijioke/autonlp-mono-625317956", use_auth_token=True)
|
46 |
+
|
47 |
+
tokenizer = AutoTokenizer.from_pretrained("Chijioke/autonlp-mono-625317956", use_auth_token=True)
|
48 |
+
|
49 |
+
inputs = tokenizer("I love AutoNLP", return_tensors="pt")
|
50 |
+
|
51 |
+
outputs = model(**inputs)
|
52 |
+
```
|
config.json
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoNLP",
|
3 |
+
"_num_labels": 23,
|
4 |
+
"activation": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"DistilBertForSequenceClassification"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"dim": 768,
|
10 |
+
"dropout": 0.1,
|
11 |
+
"hidden_dim": 3072,
|
12 |
+
"id2label": {
|
13 |
+
"0": "Rent",
|
14 |
+
"1": "atm_withdrawal",
|
15 |
+
"2": "atm_withdrawal_charges",
|
16 |
+
"3": "bank_charges",
|
17 |
+
"4": "bills_or_fees",
|
18 |
+
"5": "card_request_commission",
|
19 |
+
"6": "cash_deposit",
|
20 |
+
"7": "food",
|
21 |
+
"8": "health",
|
22 |
+
"9": "investment",
|
23 |
+
"10": "loan_repayment",
|
24 |
+
"11": "mature_loan_instalment",
|
25 |
+
"12": "miscellaneous",
|
26 |
+
"13": "offline_transactions",
|
27 |
+
"14": "online_transactions",
|
28 |
+
"15": "others",
|
29 |
+
"16": "phone_and_internet",
|
30 |
+
"17": "reversals",
|
31 |
+
"18": "salary",
|
32 |
+
"19": "stamp_duties_charges",
|
33 |
+
"20": "transfer",
|
34 |
+
"21": "transportation",
|
35 |
+
"22": "vat"
|
36 |
+
},
|
37 |
+
"initializer_range": 0.02,
|
38 |
+
"label2id": {
|
39 |
+
"Rent": 0,
|
40 |
+
"atm_withdrawal": 1,
|
41 |
+
"atm_withdrawal_charges": 2,
|
42 |
+
"bank_charges": 3,
|
43 |
+
"bills_or_fees": 4,
|
44 |
+
"card_request_commission": 5,
|
45 |
+
"cash_deposit": 6,
|
46 |
+
"food": 7,
|
47 |
+
"health": 8,
|
48 |
+
"investment": 9,
|
49 |
+
"loan_repayment": 10,
|
50 |
+
"mature_loan_instalment": 11,
|
51 |
+
"miscellaneous": 12,
|
52 |
+
"offline_transactions": 13,
|
53 |
+
"online_transactions": 14,
|
54 |
+
"others": 15,
|
55 |
+
"phone_and_internet": 16,
|
56 |
+
"reversals": 17,
|
57 |
+
"salary": 18,
|
58 |
+
"stamp_duties_charges": 19,
|
59 |
+
"transfer": 20,
|
60 |
+
"transportation": 21,
|
61 |
+
"vat": 22
|
62 |
+
},
|
63 |
+
"max_length": 64,
|
64 |
+
"max_position_embeddings": 512,
|
65 |
+
"model_type": "distilbert",
|
66 |
+
"n_heads": 12,
|
67 |
+
"n_layers": 6,
|
68 |
+
"pad_token_id": 0,
|
69 |
+
"padding": "max_length",
|
70 |
+
"problem_type": "single_label_classification",
|
71 |
+
"qa_dropout": 0.1,
|
72 |
+
"seq_classif_dropout": 0.2,
|
73 |
+
"sinusoidal_pos_embds": false,
|
74 |
+
"tie_weights_": true,
|
75 |
+
"torch_dtype": "float32",
|
76 |
+
"transformers_version": "4.15.0",
|
77 |
+
"vocab_size": 30522
|
78 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:826c71166a6d4d981c22b761654bd7b3c15aabcca7656808961265420daf66bc
|
3 |
+
size 267924657
|
sample_input.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f05e38cbeca1ae88124b99c1b1bb7bc57d33b7e881727790b8f6dff1f757003c
|
3 |
+
size 2034
|
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": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "AutoNLP", "tokenizer_class": "DistilBertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|