Commit From AutoTrain
Browse files- .gitattributes +3 -0
- README.md +56 -0
- config.json +136 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +20 -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 |
+
- ram119900/autotrain-data-tax_issues
|
11 |
+
co2_eq_emissions:
|
12 |
+
emissions: 0.044102887824261174
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
- Problem type: Multi-class Classification
|
18 |
+
- Model ID: 3708498778
|
19 |
+
- CO2 Emissions (in grams): 0.0441
|
20 |
+
|
21 |
+
## Validation Metrics
|
22 |
+
|
23 |
+
- Loss: 0.111
|
24 |
+
- Accuracy: 0.968
|
25 |
+
- Macro F1: 0.967
|
26 |
+
- Micro F1: 0.968
|
27 |
+
- Weighted F1: 0.969
|
28 |
+
- Macro Precision: 0.968
|
29 |
+
- Micro Precision: 0.968
|
30 |
+
- Weighted Precision: 0.971
|
31 |
+
- Macro Recall: 0.968
|
32 |
+
- Micro Recall: 0.968
|
33 |
+
- Weighted Recall: 0.968
|
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/ram119900/autotrain-tax_issues-3708498778
|
42 |
+
```
|
43 |
+
|
44 |
+
Or Python API:
|
45 |
+
|
46 |
+
```
|
47 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
48 |
+
|
49 |
+
model = AutoModelForSequenceClassification.from_pretrained("ram119900/autotrain-tax_issues-3708498778", use_auth_token=True)
|
50 |
+
|
51 |
+
tokenizer = AutoTokenizer.from_pretrained("ram119900/autotrain-tax_issues-3708498778", 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 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"_num_labels": 50,
|
4 |
+
"architectures": [
|
5 |
+
"XLMRobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"id2label": {
|
15 |
+
"0": "Question1",
|
16 |
+
"1": "Question10",
|
17 |
+
"2": "Question11",
|
18 |
+
"3": "Question12",
|
19 |
+
"4": "Question13",
|
20 |
+
"5": "Question14",
|
21 |
+
"6": "Question15",
|
22 |
+
"7": "Question16",
|
23 |
+
"8": "Question17",
|
24 |
+
"9": "Question18",
|
25 |
+
"10": "Question19",
|
26 |
+
"11": "Question2",
|
27 |
+
"12": "Question20",
|
28 |
+
"13": "Question21",
|
29 |
+
"14": "Question22",
|
30 |
+
"15": "Question23",
|
31 |
+
"16": "Question24",
|
32 |
+
"17": "Question25",
|
33 |
+
"18": "Question26",
|
34 |
+
"19": "Question27",
|
35 |
+
"20": "Question28",
|
36 |
+
"21": "Question29",
|
37 |
+
"22": "Question3",
|
38 |
+
"23": "Question30",
|
39 |
+
"24": "Question31",
|
40 |
+
"25": "Question32",
|
41 |
+
"26": "Question33",
|
42 |
+
"27": "Question34",
|
43 |
+
"28": "Question35",
|
44 |
+
"29": "Question36",
|
45 |
+
"30": "Question37",
|
46 |
+
"31": "Question38",
|
47 |
+
"32": "Question39",
|
48 |
+
"33": "Question4",
|
49 |
+
"34": "Question40",
|
50 |
+
"35": "Question41",
|
51 |
+
"36": "Question42",
|
52 |
+
"37": "Question43",
|
53 |
+
"38": "Question44",
|
54 |
+
"39": "Question45",
|
55 |
+
"40": "Question46",
|
56 |
+
"41": "Question47",
|
57 |
+
"42": "Question49",
|
58 |
+
"43": "Question5",
|
59 |
+
"44": "Question50",
|
60 |
+
"45": "Question6",
|
61 |
+
"46": "Question7",
|
62 |
+
"47": "Question8",
|
63 |
+
"48": "Question9",
|
64 |
+
"49": "question48"
|
65 |
+
},
|
66 |
+
"initializer_range": 0.02,
|
67 |
+
"intermediate_size": 4096,
|
68 |
+
"label2id": {
|
69 |
+
"Question1": 0,
|
70 |
+
"Question10": 1,
|
71 |
+
"Question11": 2,
|
72 |
+
"Question12": 3,
|
73 |
+
"Question13": 4,
|
74 |
+
"Question14": 5,
|
75 |
+
"Question15": 6,
|
76 |
+
"Question16": 7,
|
77 |
+
"Question17": 8,
|
78 |
+
"Question18": 9,
|
79 |
+
"Question19": 10,
|
80 |
+
"Question2": 11,
|
81 |
+
"Question20": 12,
|
82 |
+
"Question21": 13,
|
83 |
+
"Question22": 14,
|
84 |
+
"Question23": 15,
|
85 |
+
"Question24": 16,
|
86 |
+
"Question25": 17,
|
87 |
+
"Question26": 18,
|
88 |
+
"Question27": 19,
|
89 |
+
"Question28": 20,
|
90 |
+
"Question29": 21,
|
91 |
+
"Question3": 22,
|
92 |
+
"Question30": 23,
|
93 |
+
"Question31": 24,
|
94 |
+
"Question32": 25,
|
95 |
+
"Question33": 26,
|
96 |
+
"Question34": 27,
|
97 |
+
"Question35": 28,
|
98 |
+
"Question36": 29,
|
99 |
+
"Question37": 30,
|
100 |
+
"Question38": 31,
|
101 |
+
"Question39": 32,
|
102 |
+
"Question4": 33,
|
103 |
+
"Question40": 34,
|
104 |
+
"Question41": 35,
|
105 |
+
"Question42": 36,
|
106 |
+
"Question43": 37,
|
107 |
+
"Question44": 38,
|
108 |
+
"Question45": 39,
|
109 |
+
"Question46": 40,
|
110 |
+
"Question47": 41,
|
111 |
+
"Question49": 42,
|
112 |
+
"Question5": 43,
|
113 |
+
"Question50": 44,
|
114 |
+
"Question6": 45,
|
115 |
+
"Question7": 46,
|
116 |
+
"Question8": 47,
|
117 |
+
"Question9": 48,
|
118 |
+
"question48": 49
|
119 |
+
},
|
120 |
+
"layer_norm_eps": 1e-05,
|
121 |
+
"max_length": 64,
|
122 |
+
"max_position_embeddings": 514,
|
123 |
+
"model_type": "xlm-roberta",
|
124 |
+
"num_attention_heads": 16,
|
125 |
+
"num_hidden_layers": 24,
|
126 |
+
"output_past": true,
|
127 |
+
"pad_token_id": 1,
|
128 |
+
"padding": "max_length",
|
129 |
+
"position_embedding_type": "absolute",
|
130 |
+
"problem_type": "single_label_classification",
|
131 |
+
"torch_dtype": "float32",
|
132 |
+
"transformers_version": "4.25.1",
|
133 |
+
"type_vocab_size": 1,
|
134 |
+
"use_cache": true,
|
135 |
+
"vocab_size": 250002
|
136 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b2c64ece2711e74c3765957d0ad8addb9f54801c2fe0799b66f88f910d47712
|
3 |
+
size 2239906741
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45cf3a69915be3571b5e092b2d82d39428d9abff4bd0c79a516e36149045949a
|
3 |
+
size 17082923
|
tokenizer_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"__type": "AddedToken",
|
7 |
+
"content": "<mask>",
|
8 |
+
"lstrip": true,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"model_max_length": 512,
|
14 |
+
"name_or_path": "AutoTrain",
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"special_tokens_map_file": null,
|
18 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|