ranpox commited on
Commit
74cf193
1 Parent(s): 9bd1343
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_probs_dropout_prob": 0.1,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "gradient_checkpointing": false,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 768,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 3072,
11
+ "layer_norm_eps": 1e-05,
12
+ "max_2d_position_embeddings": 1024,
13
+ "max_position_embeddings": 514,
14
+ "model_type": "layoutlm",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 12,
17
+ "pad_token_id": 1,
18
+ "position_embedding_type": "absolute",
19
+ "tokenizer_class": "RobertaTokenizer",
20
+ "transformers_version": "4.6.1",
21
+ "type_vocab_size": 1,
22
+ "use_cache": true,
23
+ "vocab_size": 50265
24
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4ae325d670c116cadb283414bf6ee7d3a0f6c2472008a15496c865ea748963b
3
+ size 513826376
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff