model upload
Browse files- README.md +22 -0
- config.json +55 -0
- model_config.json +1 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
|
3 |
+
language:
|
4 |
+
- hu
|
5 |
+
tags:
|
6 |
+
- token-classification
|
7 |
+
license: gpl
|
8 |
+
metrics:
|
9 |
+
- F1
|
10 |
+
widget:
|
11 |
+
- text: "Bár sok megpróbáltatáson és piaci turbulencián van túl a magyar zöldségtermesztés, az elmúlt 20-30 évben nem volt példa arra, hogy akkora bizonytalansággal induljon egy év, mint az idén – mondta az Indexnek Gubacsi Péter, a Magyar Zöldség-Gyümölcs Szakmaközi Szervezet és Terméktanács (FruitVeB) alelnöke. Az ágazat szereplőinek egybehangzó véleménye szerint egyszerűen tervezhetetlen a működés úgy, hogy a hektikusan alakuló uniós energiapiaci helyzet és a rekordszinten lévő földgáz- és áramárak miatt gyakorlatilag naponta változik, hogy mennyiért tudnak energiát vagy műtrágyát venni."
|
12 |
+
|
13 |
+
---
|
14 |
+
|
15 |
+
# Hungarian named entity recognition model with four entity types: PER ORG LOC MISC
|
16 |
+
|
17 |
+
- Pretrained model used: SZTAKI-HLT/hubert-base-cc
|
18 |
+
- Finetuned on NYTK-NerKor Corpus
|
19 |
+
|
20 |
+
## Limitations
|
21 |
+
|
22 |
+
- max_seq_length = 448
|
config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "SZTAKI-HLT/hubert-base-cc",
|
3 |
+
"architectures": [
|
4 |
+
"TokenClassifier"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"finetuning_task": "nerkor_org_ner",
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8",
|
23 |
+
"9": "LABEL_9",
|
24 |
+
"10": "LABEL_10",
|
25 |
+
"11": "LABEL_11"
|
26 |
+
},
|
27 |
+
"initializer_range": 0.02,
|
28 |
+
"intermediate_size": 3072,
|
29 |
+
"label2id": {
|
30 |
+
"LABEL_0": 0,
|
31 |
+
"LABEL_1": 1,
|
32 |
+
"LABEL_10": 10,
|
33 |
+
"LABEL_11": 11,
|
34 |
+
"LABEL_2": 2,
|
35 |
+
"LABEL_3": 3,
|
36 |
+
"LABEL_4": 4,
|
37 |
+
"LABEL_5": 5,
|
38 |
+
"LABEL_6": 6,
|
39 |
+
"LABEL_7": 7,
|
40 |
+
"LABEL_8": 8,
|
41 |
+
"LABEL_9": 9
|
42 |
+
},
|
43 |
+
"layer_norm_eps": 1e-12,
|
44 |
+
"max_position_embeddings": 512,
|
45 |
+
"model_type": "bert",
|
46 |
+
"num_attention_heads": 12,
|
47 |
+
"num_hidden_layers": 12,
|
48 |
+
"pad_token_id": 0,
|
49 |
+
"position_embedding_type": "absolute",
|
50 |
+
"torch_dtype": "float32",
|
51 |
+
"transformers_version": "4.12.2",
|
52 |
+
"type_vocab_size": 2,
|
53 |
+
"use_cache": true,
|
54 |
+
"vocab_size": 32001
|
55 |
+
}
|
model_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bert_model": "SZTAKI-HLT/hubert-base-cc", "do_lower": false, "max_seq_length": 448, "num_labels": 12, "labels": ["O", "B-LOC", "B-MISC", "B-ORG", "B-PER", "I-LOC", "I-MISC", "I-ORG", "I-PER", "[CLS]", "[SEP]"]}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a648dfe4f9f738efaa12d9e1ac6ad926f7e83ea69525a79dd4fc14a7a21df7af
|
3 |
+
size 440230385
|
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_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "do_basic_tokenize": false, "never_split": null, "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, "full_tokenizer_file": null, "tokenizer_file": null, "name_or_path": "SZTAKI-HLT/hubert-base-cc", "tokenizer_class": "BertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|