Commit From AutoTrain
Browse files- .gitattributes +3 -0
- README.md +56 -0
- config.json +81 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +65 -0
- vocab.json +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 |
+
- modamsko/autotrain-data-idnt
|
11 |
+
co2_eq_emissions:
|
12 |
+
emissions: 0.015107604850034564
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
- Problem type: Multi-class Classification
|
18 |
+
- Model ID: 3689198408
|
19 |
+
- CO2 Emissions (in grams): 0.0151
|
20 |
+
|
21 |
+
## Validation Metrics
|
22 |
+
|
23 |
+
- Loss: 1.231
|
24 |
+
- Accuracy: 0.660
|
25 |
+
- Macro F1: 0.341
|
26 |
+
- Micro F1: 0.660
|
27 |
+
- Weighted F1: 0.617
|
28 |
+
- Macro Precision: 0.377
|
29 |
+
- Micro Precision: 0.660
|
30 |
+
- Weighted Precision: 0.614
|
31 |
+
- Macro Recall: 0.359
|
32 |
+
- Micro Recall: 0.660
|
33 |
+
- Weighted Recall: 0.660
|
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/modamsko/autotrain-idnt-3689198408
|
42 |
+
```
|
43 |
+
|
44 |
+
Or Python API:
|
45 |
+
|
46 |
+
```
|
47 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
48 |
+
|
49 |
+
model = AutoModelForSequenceClassification.from_pretrained("modamsko/autotrain-idnt-3689198408", use_auth_token=True)
|
50 |
+
|
51 |
+
tokenizer = AutoTokenizer.from_pretrained("modamsko/autotrain-idnt-3689198408", 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 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"_num_labels": 22,
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"id2label": {
|
16 |
+
"0": "Accreditatielijst mist",
|
17 |
+
"1": "Afvalcontainer(s) legen",
|
18 |
+
"2": "Beveiliging algemeen",
|
19 |
+
"3": "Bezoeker uitgezet vanwege invloed (drank, drugs)",
|
20 |
+
"4": "CP ON AIR",
|
21 |
+
"5": "Deur(en) open(en)",
|
22 |
+
"6": "Diefstal",
|
23 |
+
"7": "Drugs",
|
24 |
+
"8": "EHBO, onwelwording, letsel",
|
25 |
+
"9": "Hek nog open",
|
26 |
+
"10": "Hekken plaatsen",
|
27 |
+
"11": "Nooduitgang (geblokkeerd, onbruikbaar, etc.)",
|
28 |
+
"12": "Overig",
|
29 |
+
"13": "Post onbemand",
|
30 |
+
"14": "Schoonmaak (niet schoon)",
|
31 |
+
"15": "Schoonmaak Entr\u00e9e",
|
32 |
+
"16": "Schoonmaak Toiletten",
|
33 |
+
"17": "Storing",
|
34 |
+
"18": "Stroomprobleem",
|
35 |
+
"19": "Vechtpartij, opstoot(je), ordeverstoring",
|
36 |
+
"20": "WC papier op",
|
37 |
+
"21": "Zakkenrollers actief"
|
38 |
+
},
|
39 |
+
"initializer_range": 0.02,
|
40 |
+
"intermediate_size": 3072,
|
41 |
+
"label2id": {
|
42 |
+
"Accreditatielijst mist": 0,
|
43 |
+
"Afvalcontainer(s) legen": 1,
|
44 |
+
"Beveiliging algemeen": 2,
|
45 |
+
"Bezoeker uitgezet vanwege invloed (drank, drugs)": 3,
|
46 |
+
"CP ON AIR": 4,
|
47 |
+
"Deur(en) open(en)": 5,
|
48 |
+
"Diefstal": 6,
|
49 |
+
"Drugs": 7,
|
50 |
+
"EHBO, onwelwording, letsel": 8,
|
51 |
+
"Hek nog open": 9,
|
52 |
+
"Hekken plaatsen": 10,
|
53 |
+
"Nooduitgang (geblokkeerd, onbruikbaar, etc.)": 11,
|
54 |
+
"Overig": 12,
|
55 |
+
"Post onbemand": 13,
|
56 |
+
"Schoonmaak (niet schoon)": 14,
|
57 |
+
"Schoonmaak Entr\u00e9e": 15,
|
58 |
+
"Schoonmaak Toiletten": 16,
|
59 |
+
"Storing": 17,
|
60 |
+
"Stroomprobleem": 18,
|
61 |
+
"Vechtpartij, opstoot(je), ordeverstoring": 19,
|
62 |
+
"WC papier op": 20,
|
63 |
+
"Zakkenrollers actief": 21
|
64 |
+
},
|
65 |
+
"layer_norm_eps": 1e-05,
|
66 |
+
"max_length": 256,
|
67 |
+
"max_position_embeddings": 514,
|
68 |
+
"model_type": "roberta",
|
69 |
+
"num_attention_heads": 12,
|
70 |
+
"num_hidden_layers": 12,
|
71 |
+
"output_past": true,
|
72 |
+
"pad_token_id": 1,
|
73 |
+
"padding": "max_length",
|
74 |
+
"position_embedding_type": "absolute",
|
75 |
+
"problem_type": "single_label_classification",
|
76 |
+
"torch_dtype": "float32",
|
77 |
+
"transformers_version": "4.25.1",
|
78 |
+
"type_vocab_size": 1,
|
79 |
+
"use_cache": true,
|
80 |
+
"vocab_size": 40000
|
81 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd5f044f5162a0755f824ff51f143747dbb80d26e5b761133ee8e87e5d419c7b
|
3 |
+
size 467189493
|
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:a4ebd61597e64cb193c70e0fc217a3eaf99ce735c8789eee4181edd194ab94cb
|
3 |
+
size 1714769
|
tokenizer_config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"cls_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"eos_token": {
|
20 |
+
"__type": "AddedToken",
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"errors": "replace",
|
28 |
+
"mask_token": {
|
29 |
+
"__type": "AddedToken",
|
30 |
+
"content": "<mask>",
|
31 |
+
"lstrip": true,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
},
|
36 |
+
"model_max_length": 512,
|
37 |
+
"name_or_path": "AutoTrain",
|
38 |
+
"pad_token": {
|
39 |
+
"__type": "AddedToken",
|
40 |
+
"content": "<pad>",
|
41 |
+
"lstrip": false,
|
42 |
+
"normalized": true,
|
43 |
+
"rstrip": false,
|
44 |
+
"single_word": false
|
45 |
+
},
|
46 |
+
"sep_token": {
|
47 |
+
"__type": "AddedToken",
|
48 |
+
"content": "</s>",
|
49 |
+
"lstrip": false,
|
50 |
+
"normalized": true,
|
51 |
+
"rstrip": false,
|
52 |
+
"single_word": false
|
53 |
+
},
|
54 |
+
"special_tokens_map_file": "./robbert-v2-dutch-base/special_tokens_map.json",
|
55 |
+
"tokenizer_class": "RobertaTokenizer",
|
56 |
+
"trim_offsets": true,
|
57 |
+
"unk_token": {
|
58 |
+
"__type": "AddedToken",
|
59 |
+
"content": "<unk>",
|
60 |
+
"lstrip": false,
|
61 |
+
"normalized": true,
|
62 |
+
"rstrip": false,
|
63 |
+
"single_word": false
|
64 |
+
}
|
65 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|