First version of finbert

This commit is contained in:
Ubuntu 2020-12-24 12:41:41 +00:00
parent 61a4192dfc
commit 5fcfed04a2
5 changed files with 30559 additions and 0 deletions

32
config.json Normal file
View File

@ -0,0 +1,32 @@
{
"_name_or_path": "/home/ubuntu/finbert/models/language_model/finbertTRC2",
"architectures": [
"BertForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "positive",
"1": "negative",
"2": "neutral"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"positive": 0,
"negative": 1,
"neutral": 2
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"type_vocab_size": 2,
"vocab_size": 30522
}

BIN
pytorch_model.bin (Stored with Git LFS) Normal file

Binary file not shown.

1
special_tokens_map.json Normal file
View File

@ -0,0 +1 @@
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

1
tokenizer_config.json Normal file
View File

@ -0,0 +1 @@
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-base-uncased"}

30522
vocab.txt Normal file

File diff suppressed because it is too large Load Diff