Adding CAMeLBERT Mix NER model
Browse files- config.json +46 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-arabic-camelbert-mix-ner/",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "B-LOC",
|
13 |
+
"1": "B-MISC",
|
14 |
+
"2": "B-ORG",
|
15 |
+
"3": "B-PERS",
|
16 |
+
"4": "I-LOC",
|
17 |
+
"5": "I-MISC",
|
18 |
+
"6": "I-ORG",
|
19 |
+
"7": "I-PERS",
|
20 |
+
"8": "O"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"label2id": {
|
25 |
+
"B-LOC": 0,
|
26 |
+
"B-MISC": 1,
|
27 |
+
"B-ORG": 2,
|
28 |
+
"B-PERS": 3,
|
29 |
+
"I-LOC": 4,
|
30 |
+
"I-MISC": 5,
|
31 |
+
"I-ORG": 6,
|
32 |
+
"I-PERS": 7,
|
33 |
+
"O": 8
|
34 |
+
},
|
35 |
+
"layer_norm_eps": 1e-12,
|
36 |
+
"max_position_embeddings": 512,
|
37 |
+
"model_type": "bert",
|
38 |
+
"num_attention_heads": 12,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"pad_token_id": 0,
|
41 |
+
"position_embedding_type": "absolute",
|
42 |
+
"transformers_version": "4.3.3",
|
43 |
+
"type_vocab_size": 2,
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 30000
|
46 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfb59a2841a507a07e123b6e5f23d241a625fa506952953a368b274c57e27f16
|
3 |
+
size 436407625
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ea8e7cdb166f5891fcdca6198b2f109a652c35524ceb4149656d0006c639478
|
3 |
+
size 434276396
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "special_tokens_map_file": null, "full_tokenizer_file": null}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50b6eb92a43bcf306caebd1515aa67cf97b737ff4fe1fab3a799ec25ac2cc40f
|
3 |
+
size 1350
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|