first commit

added_tokens.json

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

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "microsoft/graphcodebert-base",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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:dbcb4dfa8c92982e25707163fb6f8db435173b91f1c7deda68edceba4c4ee38e
+size 498789873

special_tokens_map.json

@@ -0,0 +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": ["instance_variable", "number", "type_identifier", "shorthand_property_identifier_pattern", "namespace", "void_type", "heredoc_beginning", "int_literal", "comment", "heredoc_end", "none", "extends", "boolean_type", "global_variable", "property_identifier", "ERROR", "null_literal", "hash_key_symbol", "regex_flags", "shorthand_property_identifier", "string_fragment", "label_name", "escape_sequence", "boolean", "text", "character_literal", "class_variable", "integer", "string", "name", "keyword", "field_identifier", "decimal_floating_point_literal", "package_identifier", "hex_integer_literal", "\"", "float_literal", "statement_identifier", "class", "separators", "simple_symbol", "raw_string_literal", "rune_literal", "decimal_integer_literal", "operator", "string_content", "regex_pattern", "identifier", "string_literal", "php_tag", "constant", "heredoc_content"]}

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/487c9a154b15188eb68625c719ac71e12840a7b0968805e842dcb5de1531fd39.cb2244924ab24d706b02fd7fcedaea4531566537687a539ebb94db511fd122a0", "tokenizer_file": null, "name_or_path": "microsoft/graphcodebert-base", "tokenizer_class": "RobertaTokenizer"}