First model

README.md

@@ -0,0 +1,59 @@
+---
+language: id
+tags:
+- indobert
+- indobenchmark
+---
+
+## How to use
+
+### Load model and tokenizer
+```python
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+
+tokenizer = AutoTokenizer.from_pretrained("ageng-anugrah/indobert-large-p2-finetuned-ner")
+model = AutoModelForTokenClassification.from_pretrained("ageng-anugrah/indobert-large-p2-finetuned-ner")
+```
+
+### Extract NER Tag
+```python
+import torch
+def predict(model, tokenizer, sentence):
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    inputs = tokenizer(sentence.split(),
+                    is_split_into_words = True,
+                    return_offsets_mapping=True, 
+                    return_tensors="pt",
+                    padding='max_length', 
+                    truncation=True, 
+                    max_length=512)
+    
+    model.to(device)
+    # move to gpu
+    ids = inputs["input_ids"].to(device)
+    mask = inputs["attention_mask"].to(device)
+    
+    # forward pass
+    outputs = model(ids, attention_mask=mask)
+    logits = outputs[0]
+
+    active_logits = logits.view(-1, model.num_labels) # shape (batch_size * seq_len, num_labels)
+    flattened_predictions = torch.argmax(active_logits, axis=1) # shape (batch_size*seq_len,) - predictions at the token level
+
+    tokens = tokenizer.convert_ids_to_tokens(ids.squeeze().tolist())
+    token_predictions = [model.config.id2label[i] for i in flattened_predictions.cpu().numpy()]
+    wp_preds = list(zip(tokens, token_predictions)) # list of tuples. Each tuple = (wordpiece, prediction)
+
+    prediction = []
+    for token_pred, mapping in zip(wp_preds, inputs["offset_mapping"].squeeze().tolist()):
+        #only predictions on first word pieces are important
+        if mapping[0] == 0 and mapping[1] != 0:
+            prediction.append(token_pred[1])
+        else:
+            continue
+
+    return sentence.split(), prediction
+
+sentence = "BJ Habibie adalah Presiden Indonesia ke-3 yang lahir pada tanggl 25 Juni 1936"
+words, labels = predict(model, tokenizer, sentence)
+```

config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "indobenchmark/indobert-large-p2",
+  "_num_labels": 5,
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "B-ADJP",
+    "1": "B-ADVP",
+    "2": "B-INTJ",
+    "3": "B-NP",
+    "4": "B-PP",
+    "5": "B-PRT",
+    "6": "B-SBAR",
+    "7": "B-UCP",
+    "8": "B-VP",
+    "9": "I-ADJP",
+    "10": "I-ADVP",
+    "11": "I-NP",
+    "12": "I-PP",
+    "13": "I-SBAR",
+    "14": "I-UCP",
+    "15": "I-VP",
+    "16": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-ADJP": 0,
+    "B-ADVP": 1,
+    "B-INTJ": 2,
+    "B-NP": 3,
+    "B-PP": 4,
+    "B-PRT": 5,
+    "B-SBAR": 6,
+    "B-UCP": 7,
+    "B-VP": 8,
+    "I-ADJP": 9,
+    "I-ADVP": 10,
+    "I-NP": 11,
+    "I-PP": 12,
+    "I-SBAR": 13,
+    "I-UCP": 14,
+    "I-VP": 15,
+    "O": 16
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd916fb6015bfd0fe32f058ad8b444c486965293b9c5508e6e1135fac1fb015d
+size 1336577069