initial commit
Browse files- config.json +60 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +14 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForTokenClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"finetuning_task": "pos",
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "ADJ",
|
| 13 |
+
"1": "ADP",
|
| 14 |
+
"2": "ADV",
|
| 15 |
+
"3": "AUX",
|
| 16 |
+
"4": "CCONJ",
|
| 17 |
+
"5": "DET",
|
| 18 |
+
"6": "INTJ",
|
| 19 |
+
"7": "NOUN",
|
| 20 |
+
"8": "NUM",
|
| 21 |
+
"9": "PART",
|
| 22 |
+
"10": "PRON",
|
| 23 |
+
"11": "PROPN",
|
| 24 |
+
"12": "PUNCT",
|
| 25 |
+
"13": "SCONJ",
|
| 26 |
+
"14": "SYM",
|
| 27 |
+
"15": "VERB",
|
| 28 |
+
"16": "X"
|
| 29 |
+
},
|
| 30 |
+
"initializer_range": 0.02,
|
| 31 |
+
"intermediate_size": 3072,
|
| 32 |
+
"label2id": {
|
| 33 |
+
"ADJ": 0,
|
| 34 |
+
"ADP": 1,
|
| 35 |
+
"ADV": 2,
|
| 36 |
+
"AUX": 3,
|
| 37 |
+
"CCONJ": 4,
|
| 38 |
+
"DET": 5,
|
| 39 |
+
"INTJ": 6,
|
| 40 |
+
"NOUN": 7,
|
| 41 |
+
"NUM": 8,
|
| 42 |
+
"PART": 9,
|
| 43 |
+
"PRON": 10,
|
| 44 |
+
"PROPN": 11,
|
| 45 |
+
"PUNCT": 12,
|
| 46 |
+
"SCONJ": 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 |
+
"pad_token_id": 3,
|
| 57 |
+
"position_embedding_type": "absolute",
|
| 58 |
+
"type_vocab_size": 2,
|
| 59 |
+
"vocab_size": 30000
|
| 60 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e588bd6ae592dfa7e9ef6481d75bcda9562c3536a3f8170de999edc1c44305e
|
| 3 |
+
size 434101111
|
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:bd59f3cf202c52fc0b0799f80a9f27b0071dc846dcebc8bd43461a4e3924f3be
|
| 3 |
+
size 434283616
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_lower_case": false,
|
| 3 |
+
"do_basic_tokenize": true,
|
| 4 |
+
"never_split": null,
|
| 5 |
+
"unk_token": "[UNK]",
|
| 6 |
+
"sep_token": "[SEP]",
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"cls_token": "[CLS]",
|
| 9 |
+
"mask_token": "[MASK]",
|
| 10 |
+
"tokenize_chinese_chars": true,
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"model_max_length": 512,
|
| 13 |
+
"tokenizer_file": null
|
| 14 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|