GeneZC commited on
Commit
6a82c16
1 Parent(s): e25b488

Upload 5 files

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "MoEBertMiniLM"
5
+ ],
6
+ "attention_head_size": 32,
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 384,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 6144,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "moe": "1,4",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 3,
20
+ "num_relation_heads": 32,
21
+ "pad_token_id": 0,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.9.2",
25
+ "type_vocab_size": 2,
26
+ "use_cache": true,
27
+ "vocab_size": 30522
28
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15d45bede5cb489ab5dbac09e5d65e31c19c80f96487a72b152cc64cf5e232a
3
+ size 113926561
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, "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": 512, "special_tokens_map_file": null, "tokenizer_file": "/Users/gene/.cache/huggingface/transformers/475d46024228961ca8770cead39e1079f135fd2441d14cf216727ffac8d41d78.7f2721073f19841be16f41b0a70b600ca6b880c8f3df6f3535cbc704371bdfa4", "name_or_path": "/mnt/dolphinfs/ssd_pool/docker/user/hadoop-aipnlp/zhangchen76/plms/bert-large-uncased", "use_fast": true, "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff