Ensheng commited on
Commit
e8ddc87
·
1 Parent(s): 3f18b78

20221117070653/checkpoints-143000-0.0004

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"statement_identifier": 50265, "type_identifier": 50266, "int_literal": 50267, "regex_flags": 50268, "namespace": 50269, "keyword": 50270, "identifier": 50271, "escape_sequence": 50272, "class_variable": 50273, "field_identifier": 50274, "shorthand_property_identifier_pattern": 50275, "simple_symbol": 50276, "boolean": 50277, "constant": 50278, "heredoc_end": 50279, "global_variable": 50280, "php_tag": 50281, "decimal_floating_point_literal": 50282, "boolean_type": 50283, "separators": 50284, "void_type": 50285, "shorthand_property_identifier": 50286, "string_literal": 50287, "heredoc_content": 50288, "decimal_integer_literal": 50289, "extends": 50290, "instance_variable": 50291, "property_identifier": 50292, "regex_pattern": 50293, "string_fragment": 50294, "character_literal": 50295, "hash_key_symbol": 50296, "float_literal": 50297, "raw_string_literal": 50298, "rune_literal": 50299, "package_identifier": 50300, "null_literal": 50301, "string_content": 50302, "label_name": 50303, "hex_integer_literal": 50304, "heredoc_beginning": 50305}
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
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_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "transformers_version": "4.8.0",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 50306
26
+ }
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 sha256:48a7685a57a61d797665085ebcd662a8c1264fd8e0142aaf5ced731b5f0e266c
3
+ size 498789873
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["statement_identifier", "type_identifier", "int_literal", "regex_flags", "namespace", "keyword", "identifier", "escape_sequence", "class_variable", "field_identifier", "shorthand_property_identifier_pattern", "operator", "ERROR", "simple_symbol", "boolean", "constant", "heredoc_end", "global_variable", "php_tag", "decimal_floating_point_literal", "boolean_type", "\"", "separators", "void_type", "shorthand_property_identifier", "string_literal", "number", "heredoc_content", "decimal_integer_literal", "extends", "instance_variable", "property_identifier", "regex_pattern", "comment", "integer", "string_fragment", "character_literal", "hash_key_symbol", "float_literal", "raw_string_literal", "rune_literal", "package_identifier", "null_literal", "text", "class", "string_content", "label_name", "hex_integer_literal", "heredoc_beginning", "string", "name", "none"]}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/home/t-enshengshi/.cache/huggingface/transformers/d53fc0fa09b8342651efd4073d75e19617b3e51287c2a535becda5808a8db287.fc9576039592f026ad76a1c231b89aee8668488c671dfbe6616bab2ed298d730", "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff