isanvicente
commited on
Commit
•
d732c17
1
Parent(s):
caf6507
Upload 7 files
Browse files- config.json +64 -0
- labels.txt +16 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/mnt/nfs/baliabideLexikalak/wordEmbedings/eu/elhBertEu",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "O",
|
13 |
+
"1": "ADJ",
|
14 |
+
"10": "PART",
|
15 |
+
"11": "PRON",
|
16 |
+
"12": "PROPN",
|
17 |
+
"13": "PUNCT",
|
18 |
+
"14": "SYM",
|
19 |
+
"15": "VERB",
|
20 |
+
"16": "X",
|
21 |
+
"2": "ADP",
|
22 |
+
"3": "ADV",
|
23 |
+
"4": "AUX",
|
24 |
+
"5": "CONJ",
|
25 |
+
"6": "DET",
|
26 |
+
"7": "INTJ",
|
27 |
+
"8": "NOUN",
|
28 |
+
"9": "NUM"
|
29 |
+
},
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 3072,
|
32 |
+
"label2id": {
|
33 |
+
"ADJ": 1,
|
34 |
+
"ADP": 2,
|
35 |
+
"ADV": 3,
|
36 |
+
"AUX": 4,
|
37 |
+
"CONJ": 5,
|
38 |
+
"DET": 6,
|
39 |
+
"INTJ": 7,
|
40 |
+
"NOUN": 8,
|
41 |
+
"NUM": 9,
|
42 |
+
"O": 0,
|
43 |
+
"PART": 10,
|
44 |
+
"PRON": 11,
|
45 |
+
"PROPN": 12,
|
46 |
+
"PUNCT": 13,
|
47 |
+
"SYM": 14,
|
48 |
+
"VERB": 15,
|
49 |
+
"X": 16
|
50 |
+
},
|
51 |
+
"layer_norm_eps": 1e-12,
|
52 |
+
"max_position_embeddings": 512,
|
53 |
+
"model_type": "bert",
|
54 |
+
"num_attention_heads": 12,
|
55 |
+
"num_hidden_layers": 12,
|
56 |
+
"output_past": true,
|
57 |
+
"pad_token_id": 3,
|
58 |
+
"position_embedding_type": "absolute",
|
59 |
+
"torch_dtype": "float32",
|
60 |
+
"transformers_version": "4.11.0",
|
61 |
+
"type_vocab_size": 2,
|
62 |
+
"use_cache": true,
|
63 |
+
"vocab_size": 50099
|
64 |
+
}
|
labels.txt
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
ADJ
|
2 |
+
ADP
|
3 |
+
ADV
|
4 |
+
AUX
|
5 |
+
CONJ
|
6 |
+
DET
|
7 |
+
INTJ
|
8 |
+
NOUN
|
9 |
+
NUM
|
10 |
+
PART
|
11 |
+
PRON
|
12 |
+
PROPN
|
13 |
+
PUNCT
|
14 |
+
SYM
|
15 |
+
VERB
|
16 |
+
X
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8406353ce1894c406c37d6bae8eea1210eaf8e3acfaf2b0e235edf6a46e8c2fa
|
3 |
+
size 495842865
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "/mnt/nfs/baliabideLexikalak/wordEmbedings/eu/elhBertEu", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|