Multi-Task Model: SentencePiece + Scaled Gold Corpus (NER F1: 0.79)

config.json

@@ -0,0 +1,27 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertModel"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": null,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.1",
+  "vocab_size": 136521
+}

label_mapping.json

@@ -0,0 +1,93 @@
+{
+  "ner_l2i": {
+    "B-ART": 0,
+    "B-EVENT": 1,
+    "B-FAC": 2,
+    "B-GPE": 3,
+    "B-LANGUAGE": 4,
+    "B-LOC": 5,
+    "B-NORP": 6,
+    "B-ORG": 7,
+    "B-OTHERS": 8,
+    "B-PERSON": 9,
+    "B-TITLE": 10,
+    "I-ART": 11,
+    "I-EVENT": 12,
+    "I-FAC": 13,
+    "I-GPE": 14,
+    "I-LANGUAGE": 15,
+    "I-LOC": 16,
+    "I-NORP": 17,
+    "I-ORG": 18,
+    "I-OTHERS": 19,
+    "I-PERSON": 20,
+    "I-TITLE": 21,
+    "O": 22
+  },
+  "pos_l2i": {
+    "ADJ": 0,
+    "ADP": 1,
+    "ADV": 2,
+    "AUX": 3,
+    "AdJ": 4,
+    "CONJ": 5,
+    "DET": 6,
+    "INTJ": 7,
+    "NOUN": 8,
+    "NUM": 9,
+    "PERIOD": 10,
+    "PRON": 11,
+    "PROPN": 12,
+    "PUNC": 13,
+    "SCON": 14,
+    "SYM": 15,
+    "VERB": 16,
+    "X": 17
+  },
+  "id2ner": {
+    "0": "B-ART",
+    "1": "B-EVENT",
+    "2": "B-FAC",
+    "3": "B-GPE",
+    "4": "B-LANGUAGE",
+    "5": "B-LOC",
+    "6": "B-NORP",
+    "7": "B-ORG",
+    "8": "B-OTHERS",
+    "9": "B-PERSON",
+    "10": "B-TITLE",
+    "11": "I-ART",
+    "12": "I-EVENT",
+    "13": "I-FAC",
+    "14": "I-GPE",
+    "15": "I-LANGUAGE",
+    "16": "I-LOC",
+    "17": "I-NORP",
+    "18": "I-ORG",
+    "19": "I-OTHERS",
+    "20": "I-PERSON",
+    "21": "I-TITLE",
+    "22": "O"
+  },
+  "id2pos": {
+    "0": "ADJ",
+    "1": "ADP",
+    "2": "ADV",
+    "3": "AUX",
+    "4": "AdJ",
+    "5": "CONJ",
+    "6": "DET",
+    "7": "INTJ",
+    "8": "NOUN",
+    "9": "NUM",
+    "10": "PERIOD",
+    "11": "PRON",
+    "12": "PROPN",
+    "13": "PUNC",
+    "14": "SCON",
+    "15": "SYM",
+    "16": "VERB",
+    "17": "X"
+  },
+  "metrics_notes": "Validated on 80/20 Split. NER Macro F1: 0.79, POS Weighted F1: 0.97, Sentiment Acc: 1.00"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:436c211df9d41642412dcb21540487e2bd4e13f84856ba28dad5c8e79979149a
+size 591091544

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6016281caba639bb507b6c22872f658b8651b2f15ae5123afebf7cbe62a5d1f5
+size 591255243

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}