First model version
Browse files- added_tokens.json +1 -0
- bpe.codes +0 -0
- config.json +67 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<mask>": 64000}
|
bpe.codes
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "vinai/bertweet-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "ADJ",
|
| 16 |
+
"1": "ADP",
|
| 17 |
+
"2": "ADV",
|
| 18 |
+
"3": "AUX",
|
| 19 |
+
"4": "CCONJ",
|
| 20 |
+
"5": "DET",
|
| 21 |
+
"6": "INTJ",
|
| 22 |
+
"7": "NOUN",
|
| 23 |
+
"8": "NUM",
|
| 24 |
+
"9": "PART",
|
| 25 |
+
"10": "PRON",
|
| 26 |
+
"11": "PROPN",
|
| 27 |
+
"12": "PUNCT",
|
| 28 |
+
"13": "SCONJ",
|
| 29 |
+
"14": "SYM",
|
| 30 |
+
"15": "VERB",
|
| 31 |
+
"16": "X"
|
| 32 |
+
},
|
| 33 |
+
"initializer_range": 0.02,
|
| 34 |
+
"intermediate_size": 3072,
|
| 35 |
+
"label2id": {
|
| 36 |
+
"ADJ": 0,
|
| 37 |
+
"ADP": 1,
|
| 38 |
+
"ADV": 2,
|
| 39 |
+
"AUX": 3,
|
| 40 |
+
"CCONJ": 4,
|
| 41 |
+
"DET": 5,
|
| 42 |
+
"INTJ": 6,
|
| 43 |
+
"NOUN": 7,
|
| 44 |
+
"NUM": 8,
|
| 45 |
+
"PART": 9,
|
| 46 |
+
"PRON": 10,
|
| 47 |
+
"PROPN": 11,
|
| 48 |
+
"PUNCT": 12,
|
| 49 |
+
"SCONJ": 13,
|
| 50 |
+
"SYM": 14,
|
| 51 |
+
"VERB": 15,
|
| 52 |
+
"X": 16
|
| 53 |
+
},
|
| 54 |
+
"layer_norm_eps": 1e-05,
|
| 55 |
+
"max_position_embeddings": 130,
|
| 56 |
+
"model_type": "roberta",
|
| 57 |
+
"num_attention_heads": 12,
|
| 58 |
+
"num_hidden_layers": 12,
|
| 59 |
+
"pad_token_id": 1,
|
| 60 |
+
"position_embedding_type": "absolute",
|
| 61 |
+
"tokenizer_class": "BertweetTokenizer",
|
| 62 |
+
"torch_dtype": "float32",
|
| 63 |
+
"transformers_version": "4.12.5",
|
| 64 |
+
"type_vocab_size": 1,
|
| 65 |
+
"use_cache": true,
|
| 66 |
+
"vocab_size": 64001
|
| 67 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53ef3a4a03c6d00c9d9470c6f6043ecc97ebe28eacf2c06961a5e6cdb182493d
|
| 3 |
+
size 537371441
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"normalization": false, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 128, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "vinai/bertweet-base", "tokenizer_class": "BertweetTokenizer"}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7ae5da3d5ec8820196a7c44f2b8a056dc59857470da25a4c22791d3b45aaedd
|
| 3 |
+
size 2863
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|