Commit From AutoTrain
Browse files- .gitattributes +3 -0
- README.md +56 -0
- config.json +152 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +19 -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 |
+
- unk
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain"
|
9 |
+
datasets:
|
10 |
+
- IDQO/autotrain-data-liantis-profession-matcher-v08112023
|
11 |
+
co2_eq_emissions:
|
12 |
+
emissions: 3.4066803387941684
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
- Problem type: Multi-class Classification
|
18 |
+
- Model ID: 100063147551
|
19 |
+
- CO2 Emissions (in grams): 3.4067
|
20 |
+
|
21 |
+
## Validation Metrics
|
22 |
+
|
23 |
+
- Loss: 0.604
|
24 |
+
- Accuracy: 0.885
|
25 |
+
- Macro F1: 0.805
|
26 |
+
- Micro F1: 0.885
|
27 |
+
- Weighted F1: 0.871
|
28 |
+
- Macro Precision: 0.816
|
29 |
+
- Micro Precision: 0.885
|
30 |
+
- Weighted Precision: 0.868
|
31 |
+
- Macro Recall: 0.811
|
32 |
+
- Micro Recall: 0.885
|
33 |
+
- Weighted Recall: 0.885
|
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/IDQO/autotrain-liantis-profession-matcher-v08112023-100063147551
|
42 |
+
```
|
43 |
+
|
44 |
+
Or Python API:
|
45 |
+
|
46 |
+
```
|
47 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
48 |
+
|
49 |
+
model = AutoModelForSequenceClassification.from_pretrained("IDQO/autotrain-liantis-profession-matcher-v08112023-100063147551", use_auth_token=True)
|
50 |
+
|
51 |
+
tokenizer = AutoTokenizer.from_pretrained("IDQO/autotrain-liantis-profession-matcher-v08112023-100063147551", 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 +1,152 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"_num_labels": 58,
|
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": "Administratief Medewerker",
|
16 |
+
"1": "Afbraakwerker",
|
17 |
+
"2": "Arbeider",
|
18 |
+
"3": "Arbeider Handlanger",
|
19 |
+
"4": "Arbeider Ruwbouw",
|
20 |
+
"5": "Architect",
|
21 |
+
"6": "Asbestverwijderaar",
|
22 |
+
"7": "Bekister",
|
23 |
+
"8": "Betonwerker",
|
24 |
+
"9": "Bouwplaatsmachinist",
|
25 |
+
"10": "Buiten schrijnwerker",
|
26 |
+
"11": "Chauffeur",
|
27 |
+
"12": "Dakwerker",
|
28 |
+
"13": "Dekvloerlegger",
|
29 |
+
"14": "Duiker",
|
30 |
+
"15": "Elektricien",
|
31 |
+
"16": "Gevelrenoveerder",
|
32 |
+
"17": "Grondwerker",
|
33 |
+
"18": "Heating Ventilation & Airconditioning Technieker",
|
34 |
+
"19": "Ingenieur",
|
35 |
+
"20": "Installateur",
|
36 |
+
"21": "Isolatiewerker",
|
37 |
+
"22": "Keukenplaatser",
|
38 |
+
"23": "Klinkerlegger",
|
39 |
+
"24": "Kraanmachinist",
|
40 |
+
"25": "Landbouw Medewerker",
|
41 |
+
"26": "Landmeter",
|
42 |
+
"27": "Lasser",
|
43 |
+
"28": "Logistiek Medewerker",
|
44 |
+
"29": "Loodgieter",
|
45 |
+
"30": "Manager",
|
46 |
+
"31": "Mecanicien",
|
47 |
+
"32": "Metaalbewerker",
|
48 |
+
"33": "Metselaar",
|
49 |
+
"34": "Onderhoudstechnieker",
|
50 |
+
"35": "Ploegbaas",
|
51 |
+
"36": "Polierder",
|
52 |
+
"37": "Productie Medewerker",
|
53 |
+
"38": "Rioolwerker",
|
54 |
+
"39": "Ruwbouwwerken",
|
55 |
+
"40": "Schilder / Decorateur",
|
56 |
+
"41": "Schoonmaker",
|
57 |
+
"42": "Schrijnwerker",
|
58 |
+
"43": "Spoorarbeider",
|
59 |
+
"44": "Steenbewerker",
|
60 |
+
"45": "Steigerbouwer",
|
61 |
+
"46": "Stukadoor",
|
62 |
+
"47": "Technieker",
|
63 |
+
"48": "Technieker Zonnepanelen",
|
64 |
+
"49": "Technisch Tekenaar",
|
65 |
+
"50": "Timmerman",
|
66 |
+
"51": "Trappenmaker",
|
67 |
+
"52": "Vloerder / Tegelzetter",
|
68 |
+
"53": "Voeger",
|
69 |
+
"54": "Wand en plafond plaatsers",
|
70 |
+
"55": "Wegenbouwer",
|
71 |
+
"56": "Werfleider",
|
72 |
+
"57": "Zwembad Bouwer"
|
73 |
+
},
|
74 |
+
"initializer_range": 0.02,
|
75 |
+
"intermediate_size": 4096,
|
76 |
+
"label2id": {
|
77 |
+
"Administratief Medewerker": 0,
|
78 |
+
"Afbraakwerker": 1,
|
79 |
+
"Arbeider": 2,
|
80 |
+
"Arbeider Handlanger": 3,
|
81 |
+
"Arbeider Ruwbouw": 4,
|
82 |
+
"Architect": 5,
|
83 |
+
"Asbestverwijderaar": 6,
|
84 |
+
"Bekister": 7,
|
85 |
+
"Betonwerker": 8,
|
86 |
+
"Bouwplaatsmachinist": 9,
|
87 |
+
"Buiten schrijnwerker": 10,
|
88 |
+
"Chauffeur": 11,
|
89 |
+
"Dakwerker": 12,
|
90 |
+
"Dekvloerlegger": 13,
|
91 |
+
"Duiker": 14,
|
92 |
+
"Elektricien": 15,
|
93 |
+
"Gevelrenoveerder": 16,
|
94 |
+
"Grondwerker": 17,
|
95 |
+
"Heating Ventilation & Airconditioning Technieker": 18,
|
96 |
+
"Ingenieur": 19,
|
97 |
+
"Installateur": 20,
|
98 |
+
"Isolatiewerker": 21,
|
99 |
+
"Keukenplaatser": 22,
|
100 |
+
"Klinkerlegger": 23,
|
101 |
+
"Kraanmachinist": 24,
|
102 |
+
"Landbouw Medewerker": 25,
|
103 |
+
"Landmeter": 26,
|
104 |
+
"Lasser": 27,
|
105 |
+
"Logistiek Medewerker": 28,
|
106 |
+
"Loodgieter": 29,
|
107 |
+
"Manager": 30,
|
108 |
+
"Mecanicien": 31,
|
109 |
+
"Metaalbewerker": 32,
|
110 |
+
"Metselaar": 33,
|
111 |
+
"Onderhoudstechnieker": 34,
|
112 |
+
"Ploegbaas": 35,
|
113 |
+
"Polierder": 36,
|
114 |
+
"Productie Medewerker": 37,
|
115 |
+
"Rioolwerker": 38,
|
116 |
+
"Ruwbouwwerken": 39,
|
117 |
+
"Schilder / Decorateur": 40,
|
118 |
+
"Schoonmaker": 41,
|
119 |
+
"Schrijnwerker": 42,
|
120 |
+
"Spoorarbeider": 43,
|
121 |
+
"Steenbewerker": 44,
|
122 |
+
"Steigerbouwer": 45,
|
123 |
+
"Stukadoor": 46,
|
124 |
+
"Technieker": 47,
|
125 |
+
"Technieker Zonnepanelen": 48,
|
126 |
+
"Technisch Tekenaar": 49,
|
127 |
+
"Timmerman": 50,
|
128 |
+
"Trappenmaker": 51,
|
129 |
+
"Vloerder / Tegelzetter": 52,
|
130 |
+
"Voeger": 53,
|
131 |
+
"Wand en plafond plaatsers": 54,
|
132 |
+
"Wegenbouwer": 55,
|
133 |
+
"Werfleider": 56,
|
134 |
+
"Zwembad Bouwer": 57
|
135 |
+
},
|
136 |
+
"layer_norm_eps": 1e-05,
|
137 |
+
"max_length": 64,
|
138 |
+
"max_position_embeddings": 514,
|
139 |
+
"model_type": "xlm-roberta",
|
140 |
+
"num_attention_heads": 16,
|
141 |
+
"num_hidden_layers": 24,
|
142 |
+
"output_past": true,
|
143 |
+
"pad_token_id": 1,
|
144 |
+
"padding": "max_length",
|
145 |
+
"position_embedding_type": "absolute",
|
146 |
+
"problem_type": "single_label_classification",
|
147 |
+
"torch_dtype": "float32",
|
148 |
+
"transformers_version": "4.29.2",
|
149 |
+
"type_vocab_size": 1,
|
150 |
+
"use_cache": true,
|
151 |
+
"vocab_size": 250002
|
152 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d22da4c63a4afd741af19b029430eefe5dfffc5439633818bd51a646136aefcf
|
3 |
+
size 2239852480
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa1ac9afea62fca2f2fa6613b5cb55bbfdeb0c4f80dcf34af72bd1a362bf2663
|
3 |
+
size 2239939509
|
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 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "<mask>",
|
9 |
+
"lstrip": true,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"model_max_length": 512,
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
18 |
+
"unk_token": "<unk>"
|
19 |
+
}
|