commit from Ensheng

added_tokens.json

@@ -0,0 +1 @@
+{"string_content": 51416, "global_variable": 51417, "field_identifier": 51418, "instance_variable": 51419, "string_fragment": 51420, "float_literal": 51421, "simple_symbol": 51422, "class_variable": 51423, "decimal_floating_point_literal": 51424, "shorthand_property_identifier": 51425, "escape_sequence": 51426, "boolean_type": 51427, "label_name": 51428, "property_identifier": 51429, "null_literal": 51430, "hash_key_symbol": 51431, "raw_string_literal": 51432, "shorthand_property_identifier_pattern": 51433, "type_identifier": 51434, "heredoc_beginning": 51435, "php_tag": 51436, "package_identifier": 51437, "separators": 51438, "hex_integer_literal": 51439, "heredoc_end": 51440, "character_literal": 51441, "regex_pattern": 51442, "statement_identifier": 51443, "string_literal": 51444, "decimal_integer_literal": 51445, "regex_flags": 51446, "void_type": 51447, "rune_literal": 51448, "int_literal": 51449, "heredoc_content": 51450}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "microsoft/unixcoder-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": 1026,
+  "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": 10,
+  "use_cache": true,
+  "vocab_size": 51451
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f3ecebf18c951dba012ca368359981251660c0783fb89ec14e3cf69445f1d8
+size 503911921

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": ["string_content", "global_variable", "constant", "field_identifier", "none", "instance_variable", "string_fragment", "float_literal", "simple_symbol", "class_variable", "decimal_floating_point_literal", "shorthand_property_identifier", "comment", "escape_sequence", "text", "boolean_type", "\"", "label_name", "keyword", "property_identifier", "null_literal", "hash_key_symbol", "raw_string_literal", "shorthand_property_identifier_pattern", "type_identifier", "heredoc_beginning", "name", "identifier", "php_tag", "package_identifier", "namespace", "separators", "ERROR", "number", "hex_integer_literal", "boolean", "heredoc_end", "character_literal", "operator", "regex_pattern", "extends", "string", "integer", "statement_identifier", "string_literal", "decimal_integer_literal", "class", "regex_flags", "void_type", "rune_literal", "int_literal", "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"}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "microsoft/unixcoder-base", "tokenizer_class": "RobertaTokenizer"}