first commit

added_tokens.json

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

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-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,
+  "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:a29d6645f48526a6aa015d25ce4eae7dfec60d12806b2cddfb1b1c5c22651c39
+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": ["label_name", "regex_pattern", "package_identifier", "hex_integer_literal", "string_literal", "field_identifier", "separators", "php_tag", "heredoc_content", "integer", "global_variable", "null_literal", "property_identifier", "class", "string_content", "constant", "identifier", "hash_key_symbol", "decimal_integer_literal", "escape_sequence", "none", "comment", "string", "class_variable", "void_type", "string_fragment", "boolean_type", "\"", "number", "instance_variable", "heredoc_end", "type_identifier", "float_literal", "rune_literal", "statement_identifier", "namespace", "boolean", "shorthand_property_identifier_pattern", "character_literal", "operator", "shorthand_property_identifier", "heredoc_beginning", "extends", "decimal_floating_point_literal", "ERROR", "int_literal", "raw_string_literal", "regex_flags", "text", "keyword", "name", "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": null, "tokenizer_file": "/home/t-enshengshi/.cache/huggingface/transformers/d53fc0fa09b8342651efd4073d75e19617b3e51287c2a535becda5808a8db287.fc9576039592f026ad76a1c231b89aee8668488c671dfbe6616bab2ed298d730", "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}