hhou435 commited on
Commit
299c461
1 Parent(s): bbbf660
README.md ADDED
@@ -0,0 +1 @@
 
1
+ BART-medium
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bart",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "BartForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 0,
10
+ "classifier_dropout": 0.0,
11
+ "d_model": 768,
12
+ "decoder_attention_heads": 12,
13
+ "decoder_ffn_dim": 3072,
14
+ "decoder_layerdrop": 0.1,
15
+ "decoder_layers": 4,
16
+ "decoder_start_token_id": 101,
17
+ "dropout": 0.1,
18
+ "early_stopping": true,
19
+ "encoder_attention_heads": 12,
20
+ "encoder_ffn_dim": 3072,
21
+ "encoder_layerdrop": 0.1,
22
+ "encoder_layers": 4,
23
+ "eos_token_id": 0,
24
+ "forced_eos_token_id": 0,
25
+ "gradient_checkpointing": false,
26
+ "id2label": {
27
+ "0": "LABEL_0",
28
+ "1": "LABEL_1",
29
+ "2": "LABEL_2"
30
+ },
31
+ "init_std": 0.02,
32
+ "is_encoder_decoder": true,
33
+ "label2id": {
34
+ "LABEL_0": 0,
35
+ "LABEL_1": 1,
36
+ "LABEL_2": 2
37
+ },
38
+ "max_position_embeddings": 1024,
39
+ "model_type": "bart",
40
+ "num_hidden_layers": 4,
41
+ "pad_token_id": 0,
42
+ "scale_embedding": false,
43
+ "tie_word_embeddings": 0,
44
+ "tokenizer_class": "BertTokenizer",
45
+ "transformers_version": "4.6.0",
46
+ "use_cache": true,
47
+ "vocab_size": 21128
48
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81f4bd84c6be0a610aa38934b3adf7992ac46396b563045b1cb4bc42e2840594
3
+ size 400912567
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": false, "do_basic_tokenize": true, "never_split": null, "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": 128, "special_tokens_map_file": "gpt2-base-chinese-cluecorpussmall\\special_tokens_map.json", "tokenizer_file": null, "name_or_path": "bart-base-chinese-cluecorpussmall"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff