Commit From AutoTrain
Browse files- .gitattributes +3 -0
- README.md +56 -0
- config.json +86 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +3 -0
- tokenizer_config.json +16 -0
- vocab.txt +0 -0
.gitattributes
CHANGED
@@ -32,3 +32,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
37 |
+
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 |
+
- unk
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain 🤗"
|
9 |
+
datasets:
|
10 |
+
- Sergim/autotrain-data-party-words
|
11 |
+
co2_eq_emissions:
|
12 |
+
emissions: 0.015528253067718857
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
- Problem type: Multi-class Classification
|
18 |
+
- Model ID: 49350119320
|
19 |
+
- CO2 Emissions (in grams): 0.0155
|
20 |
+
|
21 |
+
## Validation Metrics
|
22 |
+
|
23 |
+
- Loss: 1.949
|
24 |
+
- Accuracy: 0.439
|
25 |
+
- Macro F1: 0.361
|
26 |
+
- Micro F1: 0.439
|
27 |
+
- Weighted F1: 0.427
|
28 |
+
- Macro Precision: 0.513
|
29 |
+
- Micro Precision: 0.439
|
30 |
+
- Weighted Precision: 0.456
|
31 |
+
- Macro Recall: 0.332
|
32 |
+
- Micro Recall: 0.439
|
33 |
+
- Weighted Recall: 0.439
|
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/Sergim/autotrain-party-words-49350119320
|
42 |
+
```
|
43 |
+
|
44 |
+
Or Python API:
|
45 |
+
|
46 |
+
```
|
47 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
48 |
+
|
49 |
+
model = AutoModelForSequenceClassification.from_pretrained("Sergim/autotrain-party-words-49350119320", use_auth_token=True)
|
50 |
+
|
51 |
+
tokenizer = AutoTokenizer.from_pretrained("Sergim/autotrain-party-words-49350119320", 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 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"_num_labels": 23,
|
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": "AVANTE",
|
15 |
+
"1": "CIDADANIA",
|
16 |
+
"2": "MDB",
|
17 |
+
"3": "NOVO",
|
18 |
+
"4": "PATRIOTA",
|
19 |
+
"5": "PCdoB",
|
20 |
+
"6": "PDT",
|
21 |
+
"7": "PL",
|
22 |
+
"8": "PODE",
|
23 |
+
"9": "PP",
|
24 |
+
"10": "PROS",
|
25 |
+
"11": "PSB",
|
26 |
+
"12": "PSC",
|
27 |
+
"13": "PSD",
|
28 |
+
"14": "PSDB",
|
29 |
+
"15": "PSOL",
|
30 |
+
"16": "PT",
|
31 |
+
"17": "PTB",
|
32 |
+
"18": "PV",
|
33 |
+
"19": "REDE",
|
34 |
+
"20": "REPUBLICANOS",
|
35 |
+
"21": "SOLIDARIEDADE",
|
36 |
+
"22": "UNI\u00c3O"
|
37 |
+
},
|
38 |
+
"initializer_range": 0.02,
|
39 |
+
"intermediate_size": 3072,
|
40 |
+
"label2id": {
|
41 |
+
"AVANTE": 0,
|
42 |
+
"CIDADANIA": 1,
|
43 |
+
"MDB": 2,
|
44 |
+
"NOVO": 3,
|
45 |
+
"PATRIOTA": 4,
|
46 |
+
"PCdoB": 5,
|
47 |
+
"PDT": 6,
|
48 |
+
"PL": 7,
|
49 |
+
"PODE": 8,
|
50 |
+
"PP": 9,
|
51 |
+
"PROS": 10,
|
52 |
+
"PSB": 11,
|
53 |
+
"PSC": 12,
|
54 |
+
"PSD": 13,
|
55 |
+
"PSDB": 14,
|
56 |
+
"PSOL": 15,
|
57 |
+
"PT": 16,
|
58 |
+
"PTB": 17,
|
59 |
+
"PV": 18,
|
60 |
+
"REDE": 19,
|
61 |
+
"REPUBLICANOS": 20,
|
62 |
+
"SOLIDARIEDADE": 21,
|
63 |
+
"UNI\u00c3O": 22
|
64 |
+
},
|
65 |
+
"layer_norm_eps": 1e-12,
|
66 |
+
"max_length": 512,
|
67 |
+
"max_position_embeddings": 512,
|
68 |
+
"model_type": "bert",
|
69 |
+
"num_attention_heads": 12,
|
70 |
+
"num_hidden_layers": 12,
|
71 |
+
"output_past": true,
|
72 |
+
"pad_token_id": 0,
|
73 |
+
"padding": "max_length",
|
74 |
+
"pooler_fc_size": 768,
|
75 |
+
"pooler_num_attention_heads": 12,
|
76 |
+
"pooler_num_fc_layers": 3,
|
77 |
+
"pooler_size_per_head": 128,
|
78 |
+
"pooler_type": "first_token_transform",
|
79 |
+
"position_embedding_type": "absolute",
|
80 |
+
"problem_type": "single_label_classification",
|
81 |
+
"torch_dtype": "float32",
|
82 |
+
"transformers_version": "4.25.1",
|
83 |
+
"type_vocab_size": 2,
|
84 |
+
"use_cache": true,
|
85 |
+
"vocab_size": 29794
|
86 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f74b03c24a1374252299f5ce4f39b95586751392e021c7e0b62fa11c803549c1
|
3 |
+
size 435836085
|
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 sha256:1e0f07993dcfa9b2d64d389790ba3e9b197738ed669a6cf2ab92c58662e594cc
|
3 |
+
size 678055
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"name_or_path": "AutoTrain",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": "/app/.cache/huggingface/hub/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/special_tokens_map.json",
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|