Upload 9 files
Browse files- added_tokens.json +7 -0
- config.json +52 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +63 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<mask>": 4,
|
4 |
+
"<pad>": 1,
|
5 |
+
"<s>": 0,
|
6 |
+
"<unk>": 3
|
7 |
+
}
|
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "models/PuoBERTa-resume-v4",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "arts_culture_entertainment_and_media",
|
15 |
+
"1": "crime_law_and_justice",
|
16 |
+
"2": "disaster_accident_and_emergency_incident",
|
17 |
+
"3": "economy_business_and_finance",
|
18 |
+
"4": "education",
|
19 |
+
"5": "environment",
|
20 |
+
"6": "health",
|
21 |
+
"7": "politics",
|
22 |
+
"8": "religion_and_belief",
|
23 |
+
"9": "society"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 3072,
|
27 |
+
"label2id": {
|
28 |
+
"arts_culture_entertainment_and_media": 0,
|
29 |
+
"crime_law_and_justice": 1,
|
30 |
+
"disaster_accident_and_emergency_incident": 2,
|
31 |
+
"economy_business_and_finance": 3,
|
32 |
+
"education": 4,
|
33 |
+
"environment": 5,
|
34 |
+
"health": 6,
|
35 |
+
"politics": 7,
|
36 |
+
"religion_and_belief": 8,
|
37 |
+
"society": 9
|
38 |
+
},
|
39 |
+
"layer_norm_eps": 1e-12,
|
40 |
+
"max_position_embeddings": 514,
|
41 |
+
"model_type": "roberta",
|
42 |
+
"num_attention_heads": 12,
|
43 |
+
"num_hidden_layers": 6,
|
44 |
+
"pad_token_id": 1,
|
45 |
+
"position_embedding_type": "absolute",
|
46 |
+
"problem_type": "single_label_classification",
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.34.0",
|
49 |
+
"type_vocab_size": 1,
|
50 |
+
"use_cache": true,
|
51 |
+
"vocab_size": 52000
|
52 |
+
}
|
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 sha256:63f49833ecbd54763e317f574e73ce3b70570c51ebf87908e296a06a22e35e31
|
3 |
+
size 333870001
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"additional_special_tokens": [],
|
46 |
+
"bos_token": "<s>",
|
47 |
+
"clean_up_tokenization_spaces": true,
|
48 |
+
"cls_token": "<s>",
|
49 |
+
"eos_token": "</s>",
|
50 |
+
"errors": "replace",
|
51 |
+
"mask_token": "<mask>",
|
52 |
+
"max_len": 512,
|
53 |
+
"max_length": 512,
|
54 |
+
"model_max_length": 512,
|
55 |
+
"pad_token": "<pad>",
|
56 |
+
"sep_token": "</s>",
|
57 |
+
"stride": 0,
|
58 |
+
"tokenizer_class": "RobertaTokenizer",
|
59 |
+
"trim_offsets": true,
|
60 |
+
"truncation_side": "right",
|
61 |
+
"truncation_strategy": "longest_first",
|
62 |
+
"unk_token": "<unk>"
|
63 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a348e138af095cca18a62179965eb87ecb7cd56b7db7f0622324443ccc56476
|
3 |
+
size 4155
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|