Upload folder using huggingface_hub
Browse files- config.json +24 -0
- edge_pattern_stats.json +0 -0
- label2id.json +64 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"transformers_version": "4.57.0",
|
| 21 |
+
"type_vocab_size": 2,
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
edge_pattern_stats.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
label2id.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"UNK": 0,
|
| 3 |
+
"variable": 1,
|
| 4 |
+
"body": 2,
|
| 5 |
+
"as:modification": 3,
|
| 6 |
+
"as:punctuation": 4,
|
| 7 |
+
"next_word": 5,
|
| 8 |
+
"func.arg": 6,
|
| 9 |
+
"pred.arg.1": 7,
|
| 10 |
+
"pred.arg.2": 8,
|
| 11 |
+
"@modification": 9,
|
| 12 |
+
"@expression": 10,
|
| 13 |
+
"@attribute": 11,
|
| 14 |
+
"as:@modification": 12,
|
| 15 |
+
"@parataxis": 13,
|
| 16 |
+
"pred.arg.4": 14,
|
| 17 |
+
"@@modification": 15,
|
| 18 |
+
"as:discourse": 16,
|
| 19 |
+
"punctuation": 17,
|
| 20 |
+
"as:@modification+pred.arg.2": 18,
|
| 21 |
+
"as:@modification+pred.arg.3": 19,
|
| 22 |
+
"@ref+pred.arg.1": 20,
|
| 23 |
+
"pred.arg.3": 21,
|
| 24 |
+
"@ref": 22,
|
| 25 |
+
"as:@modification+body": 23,
|
| 26 |
+
"as:@modification+pred.arg.1": 24,
|
| 27 |
+
"@vocative": 25,
|
| 28 |
+
"@@attribute": 26,
|
| 29 |
+
"@copula": 27,
|
| 30 |
+
"as:vocative": 28,
|
| 31 |
+
"@appositive": 29,
|
| 32 |
+
"@@expression": 30,
|
| 33 |
+
"@list": 31,
|
| 34 |
+
"as:@@modification+pred.arg.1": 32,
|
| 35 |
+
"as:@@modification": 33,
|
| 36 |
+
"as:@ref": 34,
|
| 37 |
+
"@@list": 35,
|
| 38 |
+
"@@parataxis": 36,
|
| 39 |
+
"@appositive+pred.arg.2": 37,
|
| 40 |
+
"as:func.arg": 38,
|
| 41 |
+
"@discourse": 39,
|
| 42 |
+
"@@ref": 40,
|
| 43 |
+
"@@@list": 41,
|
| 44 |
+
"@@@modification": 42,
|
| 45 |
+
"as:@@modification+pred.arg.2": 43,
|
| 46 |
+
"as:@@ref": 44,
|
| 47 |
+
"@modification+pred.arg.2": 45,
|
| 48 |
+
"@@appositive": 46,
|
| 49 |
+
"as:pred.arg.2": 47,
|
| 50 |
+
"as:pred.arg.1": 48,
|
| 51 |
+
"as:repeat": 49,
|
| 52 |
+
"@vocative+pred.arg.1": 50,
|
| 53 |
+
"as:@appositive": 51,
|
| 54 |
+
"as:@attribute": 52,
|
| 55 |
+
"@modification+pred.arg.1": 53,
|
| 56 |
+
"@@@modification+@@modification": 54,
|
| 57 |
+
"@ref+pred.arg.2": 55,
|
| 58 |
+
"@@@appositive": 56,
|
| 59 |
+
"@@modification+pred.arg.2": 57,
|
| 60 |
+
"as:@@@ref": 58,
|
| 61 |
+
"as:@@@@modification": 59,
|
| 62 |
+
"as:@@modification+@modification": 60,
|
| 63 |
+
"@@ref+pred.arg.1": 61
|
| 64 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:082a40d1d913e768bdcfe274a513e9fe07ae93802f27388ac6dcc1b38fc376fa
|
| 3 |
+
size 457869463
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|