Chao Jiang commited on
Commit
0c05de8
·
1 Parent(s): 0a291ea

first version of newsela-sentence-alignment fine-tuned BERTmodel and tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_probs_dropout_prob": 0.1,
3
+ "finetuning_task": "newsela_task2",
4
+ "hidden_act": "gelu",
5
+ "hidden_dropout_prob": 0.1,
6
+ "hidden_size": 768,
7
+ "initializer_range": 0.02,
8
+ "intermediate_size": 3072,
9
+ "layer_norm_eps": 1e-12,
10
+ "max_position_embeddings": 512,
11
+ "num_attention_heads": 12,
12
+ "num_hidden_layers": 12,
13
+ "num_labels": 2,
14
+ "output_attentions": false,
15
+ "output_hidden_states": false,
16
+ "pruned_heads": {},
17
+ "torchscript": false,
18
+ "type_vocab_size": 2,
19
+ "vocab_size": 30522
20
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e8ff4dd4a3155b715a2f35408fbf6a1b735a1f20aaec08ef5bee48878dfd1b3
3
+ size 437985387
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "max_len": 512, "init_inputs": []}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52eb36da7090ce585d56c69767ad03d46a3d8b5f4c5d03515added5c966858fb
3
+ size 1296
vocab.txt ADDED
The diff for this file is too large to render. See raw diff