init commit

config.json

@@ -0,0 +1,67 @@
+{
+  "_name_or_path": "csebuetnlp/banglishbert",
+  "_num_labels": 2,
+  "amp": true,
+  "architectures": [
+    "ElectraForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.4,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.4,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-Symptom",
+    "2": "I-Symptom",
+    "3": "B-Health Condition",
+    "4": "I-Health Condition",
+    "5": "B-Age",
+    "6": "I-Age",
+    "7": "B-Medicine",
+    "8": "I-Medicine",
+    "9": "B-Dosage",
+    "10": "I-Dosage",
+    "11": "B-Medical Procedure",
+    "12": "I-Medical Procedure",
+    "13": "B-Specialist",
+    "14": "I-Specialist"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Age": 5,
+    "B-Dosage": 9,
+    "B-Health Condition": 3,
+    "B-Medical Procedure": 11,
+    "B-Medicine": 7,
+    "B-Specialist": 13,
+    "B-Symptom": 1,
+    "I-Age": 6,
+    "I-Dosage": 10,
+    "I-Health Condition": 4,
+    "I-Medical Procedure": 12,
+    "I-Medicine": 8,
+    "I-Specialist": 14,
+    "I-Symptom": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4177eec99cb86ccf82e80eeee5dfbced90406dc51e66fbb55c4c7e7a47124f30
+size 440177068

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": false,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf37ab4552122a2995b84c839e26a7b4260f7cfcbb7b2ab61b8f964d5a043c2c
+size 5112