hf-transformers-bot commited on
Commit
7d007da
1 Parent(s): f0aba4b

Upload tiny models for RoCBertForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RoCBertForCausalLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "concat_input": true,
8
+ "enable_pronunciation": true,
9
+ "enable_shape": true,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 32,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 37,
15
+ "is_decoder": true,
16
+ "layer_norm_eps": 1e-12,
17
+ "max_position_embeddings": 512,
18
+ "model_type": "roc_bert",
19
+ "num_attention_heads": 4,
20
+ "num_hidden_layers": 5,
21
+ "pad_token_id": 0,
22
+ "position_embedding_type": "absolute",
23
+ "pronunciation_embed_dim": 32,
24
+ "pronunciation_vocab_size": 99,
25
+ "shape_embed_dim": 32,
26
+ "shape_vocab_size": 99,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.28.0.dev0",
29
+ "type_vocab_size": 16,
30
+ "use_cache": true,
31
+ "vocab_size": 21128
32
+ }
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.28.0.dev0"
5
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cab83cf28e50fb17c8b26f4f8fadf5219ffda455826b9f753c510c5879fa2b77
3
+ size 3069710
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "RoCBertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
word_pronunciation.json ADDED
The diff for this file is too large to render. See raw diff
 
word_shape.json ADDED
The diff for this file is too large to render. See raw diff