Upload 6 files

Browse files

Files changed (6) hide show

config.json +207 -0
merges.txt +0 -0
special_tokens_map.json +15 -0
tokenizer.json +0 -0
tokenizer_config.json +59 -0
vocab.json +0 -0

config.json ADDED Viewed

	@@ -0,0 +1,207 @@

+{
+  "_name_or_path": "kunalr63/roberta-retrained",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "O",
+    "1": "B-NAME",
+    "2": "L-NAME",
+    "3": "B-C_DESIG",
+    "4": "I-C_DESIG",
+    "5": "L-C_DESIG",
+    "6": "B-CANDIDATE_ADDRESS",
+    "7": "I-CANDIDATE_ADDRESS",
+    "8": "L-CANDIDATE_ADDRESS",
+    "9": "B-PHONE",
+    "10": "I-PHONE",
+    "11": "L-PHONE",
+    "12": "U-EMAIL",
+    "13": "U-DOB",
+    "14": "B-T_EXP",
+    "15": "I-T_EXP",
+    "16": "L-T_EXP",
+    "17": "B-EXP_COMPANY_WISE",
+    "18": "I-EXP_COMPANY_WISE",
+    "19": "L-EXP_COMPANY_WISE",
+    "20": "B-PROJECTS",
+    "21": "I-PROJECTS",
+    "22": "L-PROJECTS",
+    "23": "B-SKILLS",
+    "24": "L-SKILLS",
+    "25": "U-SKILLS",
+    "26": "I-SKILLS",
+    "27": "B-CERTIFICATE",
+    "28": "I-CERTIFICATE",
+    "29": "L-CERTIFICATE",
+    "30": "B-G_IN",
+    "31": "I-G_IN",
+    "32": "L-G_IN",
+    "33": "B-G_CLG",
+    "34": "I-G_CLG",
+    "35": "L-G_CLG",
+    "36": "U-G_YEAR",
+    "37": "U-PHONE",
+    "38": "B-HIGH_FROM",
+    "39": "L-HIGH_FROM",
+    "40": "B-HIGH_PER",
+    "41": "L-HIGH_PER",
+    "42": "B-INTER_FROM",
+    "43": "L-INTER_FROM",
+    "44": "B-INTER_PER",
+    "45": "L-INTER_PER",
+    "46": "B-GRAD_PER",
+    "47": "L-GRAD_PER",
+    "48": "B-DOB",
+    "49": "I-DOB",
+    "50": "L-DOB",
+    "51": "U-NAME",
+    "52": "B-EMAIL",
+    "53": "I-EMAIL",
+    "54": "L-EMAIL",
+    "55": "I-INTER_FROM",
+    "56": "I-HIGH_FROM",
+    "57": "I-NAME",
+    "58": "B-PG_FROM",
+    "59": "L-PG_FROM",
+    "60": "B-PG_IN",
+    "61": "I-PG_IN",
+    "62": "L-PG_IN",
+    "63": "U-PG_YEAR",
+    "64": "U-G_IN",
+    "65": "I-PG_FROM",
+    "66": "U-CANDIDATE_ADDRESS",
+    "67": "U-G_CLG",
+    "68": "U-PG_IN",
+    "69": "B-PG_YEAR",
+    "70": "I-PG_YEAR",
+    "71": "L-PG_YEAR",
+    "72": "B-G_YEAR",
+    "73": "I-G_YEAR",
+    "74": "L-G_YEAR",
+    "75": "U-PG_FROM",
+    "76": "U-INTER_FROM",
+    "77": "U-HIGH_FROM",
+    "78": "U-GRAD_PER",
+    "79": "U-INTER_PER",
+    "80": "U-HIGH_PER",
+    "81": "U-T_EXP",
+    "82": "I-GRAD_PER",
+    "83": "U-PROJECTS",
+    "84": "U-CERTIFICATE",
+    "85": "U-EXP_COMPANY_WISE",
+    "86": "I-HIGH_PER",
+    "87": "I-INTER_PER"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-CANDIDATE_ADDRESS": 6,
+    "B-CERTIFICATE": 27,
+    "B-C_DESIG": 3,
+    "B-DOB": 48,
+    "B-EMAIL": 52,
+    "B-EXP_COMPANY_WISE": 17,
+    "B-GRAD_PER": 46,
+    "B-G_CLG": 33,
+    "B-G_IN": 30,
+    "B-G_YEAR": 72,
+    "B-HIGH_FROM": 38,
+    "B-HIGH_PER": 40,
+    "B-INTER_FROM": 42,
+    "B-INTER_PER": 44,
+    "B-NAME": 1,
+    "B-PG_FROM": 58,
+    "B-PG_IN": 60,
+    "B-PG_YEAR": 69,
+    "B-PHONE": 9,
+    "B-PROJECTS": 20,
+    "B-SKILLS": 23,
+    "B-T_EXP": 14,
+    "I-CANDIDATE_ADDRESS": 7,
+    "I-CERTIFICATE": 28,
+    "I-C_DESIG": 4,
+    "I-DOB": 49,
+    "I-EMAIL": 53,
+    "I-EXP_COMPANY_WISE": 18,
+    "I-GRAD_PER": 82,
+    "I-G_CLG": 34,
+    "I-G_IN": 31,
+    "I-G_YEAR": 73,
+    "I-HIGH_FROM": 56,
+    "I-HIGH_PER": 86,
+    "I-INTER_FROM": 55,
+    "I-INTER_PER": 87,
+    "I-NAME": 57,
+    "I-PG_FROM": 65,
+    "I-PG_IN": 61,
+    "I-PG_YEAR": 70,
+    "I-PHONE": 10,
+    "I-PROJECTS": 21,
+    "I-SKILLS": 26,
+    "I-T_EXP": 15,
+    "L-CANDIDATE_ADDRESS": 8,
+    "L-CERTIFICATE": 29,
+    "L-C_DESIG": 5,
+    "L-DOB": 50,
+    "L-EMAIL": 54,
+    "L-EXP_COMPANY_WISE": 19,
+    "L-GRAD_PER": 47,
+    "L-G_CLG": 35,
+    "L-G_IN": 32,
+    "L-G_YEAR": 74,
+    "L-HIGH_FROM": 39,
+    "L-HIGH_PER": 41,
+    "L-INTER_FROM": 43,
+    "L-INTER_PER": 45,
+    "L-NAME": 2,
+    "L-PG_FROM": 59,
+    "L-PG_IN": 62,
+    "L-PG_YEAR": 71,
+    "L-PHONE": 11,
+    "L-PROJECTS": 22,
+    "L-SKILLS": 24,
+    "L-T_EXP": 16,
+    "O": 0,
+    "U-CANDIDATE_ADDRESS": 66,
+    "U-CERTIFICATE": 84,
+    "U-DOB": 13,
+    "U-EMAIL": 12,
+    "U-EXP_COMPANY_WISE": 85,
+    "U-GRAD_PER": 78,
+    "U-G_CLG": 67,
+    "U-G_IN": 64,
+    "U-G_YEAR": 36,
+    "U-HIGH_FROM": 77,
+    "U-HIGH_PER": 80,
+    "U-INTER_FROM": 76,
+    "U-INTER_PER": 79,
+    "U-NAME": 51,
+    "U-PG_FROM": 75,
+    "U-PG_IN": 68,
+    "U-PG_YEAR": 63,
+    "U-PHONE": 37,
+    "U-PROJECTS": 83,
+    "U-SKILLS": 25,
+    "U-T_EXP": 81
+  },
+  "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": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,59 @@

+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "ignore_mismatched_sizes": true,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff