ranpox commited on
Commit
9b04f18
1 Parent(s): 9572410
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<end-of-node>": 50266, "[empty-title]": 50265}
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MarkupLMForPretraining"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_depth": 50,
17
+ "max_position_embeddings": 514,
18
+ "max_xpath_subs_unit_embeddings": 1024,
19
+ "max_xpath_tag_unit_embeddings": 256,
20
+ "model_type": "markuplm",
21
+ "num_attention_heads": 12,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 1,
24
+ "position_embedding_type": "absolute",
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.10.2",
27
+ "type_vocab_size": 1,
28
+ "use_cache": true,
29
+ "vocab_size": 50267,
30
+ "xpath_unit_hidden_size": 32
31
+ }
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 sha256:812da9c91ed2b8d807c15c610fad699893ae2e7163861a2675fc162bcd834185
3
+ size 276526721
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": "markuplm-base", "tokenizer_class": "MarkupLMTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff