Initial commit
Browse files- config.json +72 -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 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/drive/MyDrive/models/electra-base-italian-xxl-cased-discriminator/checkpoint-4065",
|
3 |
+
"architectures": [
|
4 |
+
"ElectraForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"embedding_size": 768,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "I-AVV",
|
14 |
+
"1": "I-CNS",
|
15 |
+
"2": "B-RIC",
|
16 |
+
"3": "I-SNT",
|
17 |
+
"4": "B-CNS",
|
18 |
+
"5": "B-PMI",
|
19 |
+
"6": "B-AVV",
|
20 |
+
"7": "I-RCR",
|
21 |
+
"8": "B-DOM",
|
22 |
+
"9": "B-CTR",
|
23 |
+
"10": "I-CTR",
|
24 |
+
"11": "B-SNT",
|
25 |
+
"12": "I-DOM",
|
26 |
+
"13": "I-RIC",
|
27 |
+
"14": "B-RCR",
|
28 |
+
"15": "I-CDA",
|
29 |
+
"16": "I-PMI",
|
30 |
+
"17": "O",
|
31 |
+
"18": "B-CDA"
|
32 |
+
},
|
33 |
+
"initializer_range": 0.02,
|
34 |
+
"intermediate_size": 3072,
|
35 |
+
"label2id": {
|
36 |
+
"B-AVV": 6,
|
37 |
+
"B-CDA": 18,
|
38 |
+
"B-CNS": 4,
|
39 |
+
"B-CTR": 9,
|
40 |
+
"B-DOM": 8,
|
41 |
+
"B-PMI": 5,
|
42 |
+
"B-RCR": 14,
|
43 |
+
"B-RIC": 2,
|
44 |
+
"B-SNT": 11,
|
45 |
+
"I-AVV": 0,
|
46 |
+
"I-CDA": 15,
|
47 |
+
"I-CNS": 1,
|
48 |
+
"I-CTR": 10,
|
49 |
+
"I-DOM": 12,
|
50 |
+
"I-PMI": 16,
|
51 |
+
"I-RCR": 7,
|
52 |
+
"I-RIC": 13,
|
53 |
+
"I-SNT": 3,
|
54 |
+
"O": 17
|
55 |
+
},
|
56 |
+
"layer_norm_eps": 1e-12,
|
57 |
+
"max_position_embeddings": 512,
|
58 |
+
"model_type": "electra",
|
59 |
+
"num_attention_heads": 12,
|
60 |
+
"num_hidden_layers": 12,
|
61 |
+
"pad_token_id": 0,
|
62 |
+
"position_embedding_type": "absolute",
|
63 |
+
"summary_activation": "gelu",
|
64 |
+
"summary_last_dropout": 0.1,
|
65 |
+
"summary_type": "first",
|
66 |
+
"summary_use_proj": true,
|
67 |
+
"torch_dtype": "float32",
|
68 |
+
"transformers_version": "4.16.2",
|
69 |
+
"type_vocab_size": 2,
|
70 |
+
"use_cache": true,
|
71 |
+
"vocab_size": 31102
|
72 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:022bb51b90e9f63f0f749b5949e9f594d07b2b5de0362f742be8c6b5fd0feacf
|
3 |
+
size 437488689
|
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, "max_len": 512, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/content/drive/MyDrive/models/electra-base-italian-xxl-cased-discriminator/checkpoint-4065", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|