first commit

added_tokens.json

@@ -0,0 +1 @@
+{"float_literal": 50265, "void_type": 50266, "keyword": 50267, "regex_pattern": 50268, "heredoc_content": 50269, "hex_integer_literal": 50270, "extends": 50271, "package_identifier": 50272, "int_literal": 50273, "identifier": 50274, "raw_string_literal": 50275, "boolean_type": 50276, "label_name": 50277, "rune_literal": 50278, "decimal_floating_point_literal": 50279, "php_tag": 50280, "constant": 50281, "hash_key_symbol": 50282, "string_fragment": 50283, "type_identifier": 50284, "escape_sequence": 50285, "global_variable": 50286, "regex_flags": 50287, "separators": 50288, "shorthand_property_identifier_pattern": 50289, "null_literal": 50290, "instance_variable": 50291, "boolean": 50292, "string_content": 50293, "class_variable": 50294, "property_identifier": 50295, "namespace": 50296, "heredoc_end": 50297, "shorthand_property_identifier": 50298, "decimal_integer_literal": 50299, "heredoc_beginning": 50300, "field_identifier": 50301, "statement_identifier": 50302, "character_literal": 50303, "string_literal": 50304, "simple_symbol": 50305}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "microsoft/codebert-base",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50306
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba7cf018990468839865c457aba500156dbbb6311ca4f289f2ed0d2e25d923c
+size 498789873

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": ["float_literal", "void_type", "keyword", "regex_pattern", "heredoc_content", "hex_integer_literal", "extends", "package_identifier", "name", "int_literal", "integer", "identifier", "number", "comment", "raw_string_literal", "boolean_type", "label_name", "rune_literal", "decimal_floating_point_literal", "php_tag", "constant", "hash_key_symbol", "string", "string_fragment", "type_identifier", "escape_sequence", "text", "global_variable", "regex_flags", "separators", "shorthand_property_identifier_pattern", "null_literal", "instance_variable", "boolean", "ERROR", "string_content", "class_variable", "property_identifier", "\"", "namespace", "heredoc_end", "shorthand_property_identifier", "decimal_integer_literal", "heredoc_beginning", "operator", "field_identifier", "none", "statement_identifier", "class", "character_literal", "string_literal", "simple_symbol"]}

tokenizer_config.json

@@ -0,0 +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": "/home/t-enshengshi/.cache/huggingface/transformers/4da22fec5578ecec5fbe32b80d5a43c6fb66b0f6ad5e359979463f0722ac3b5f.0dc5b1041f62041ebbd23b1297f2f573769d5c97d8b7c28180ec86b8f6185aa8", "tokenizer_file": null, "name_or_path": "microsoft/codebert-base", "tokenizer_class": "RobertaTokenizer"}