Initial commit for CoditT5

added_tokens.json

@@ -0,0 +1 @@
+{"<REPLACE>": 32100, "<REPLACE_OLD>": 32101, "<REPLACE_NEW>": 32102, "<REPLACE_END>": 32103, "<REPLACE_OLD_KEEP_BEFORE>": 32104, "<REPLACE_NEW_KEEP_BEFORE>": 32105, "<REPLACE_OLD_KEEP_AFTER>": 32106, "<REPLACE_NEW_KEEP_AFTER>": 32107, "<REPLACE_OLD_DELETE_KEEP_BEFORE>": 32108, "<REPLACE_NEW_DELETE_KEEP_BEFORE>": 32109, "<REPLACE_OLD_DELETE_KEEP_AFTER>": 32110, "<REPLACE_NEW_DELETE_KEEP_AFTER>": 32111, "<INSERT>": 32112, "<INSERT_OLD>": 32113, "<INSERT_NEW>": 32114, "<INSERT_END>": 32115, "<INSERT_OLD_KEEP_BEFORE>": 32116, "<INSERT_NEW_KEEP_BEFORE>": 32117, "<INSERT_OLD_KEEP_AFTER>": 32118, "<INSERT_NEW_KEEP_AFTER>": 32119, "<DELETE>": 32120, "<DELETE_END>": 32121, "<KEEP>": 32122, "<KEEP_END>": 32123}

config.json

@@ -0,0 +1,65 @@
+{
+  "_name_or_path": "Salesforce/codet5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 2,
+  "feed_forward_proj": "relu",
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "use_cache": true,
+  "vocab_size": 32124
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ae7311a8925b7ab67c4c16224b3bff4cb51797ac1ead1b0c7768e690cc06e9c
+size 891715007

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": [{"content": "<extra_id_99>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_98>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_97>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_96>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_95>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_94>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_93>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_92>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_91>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_90>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_89>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_88>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_87>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_86>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_85>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_84>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_83>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_82>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_81>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_80>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_79>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_78>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_77>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_76>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_75>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_74>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_73>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_72>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_71>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_70>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_69>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_68>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_67>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_66>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_65>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_64>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_63>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_62>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_61>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_60>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_59>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_58>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_57>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_56>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_55>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_54>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_53>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_52>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_51>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_50>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_49>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_48>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_47>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_46>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_45>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_44>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_43>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_42>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_41>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_40>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_39>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_38>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_37>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_36>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_35>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_34>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_33>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_32>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_31>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_30>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_29>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_28>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_27>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_26>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_25>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_24>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_23>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_22>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_21>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_20>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_19>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_18>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_17>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_16>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_15>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_14>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_13>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_12>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_11>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_10>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_9>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_8>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_7>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_6>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_5>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_4>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_3>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_2>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_1>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, {"content": "<extra_id_0>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}]}

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": "/work2/06922/jiyang/maverick2/.cache/5941df5e4315c5ab63b7b2ac791fb0bf0f209744a055c06b43b5274849137cdd.b9905d0575bde443a20834122b6e2d48e853b2e36444ce98ddeb43c38097eb3f", "tokenizer_file": null, "name_or_path": "models/codeT5Tokenizer", "tokenizer_class": "RobertaTokenizer"}