Adding indobert-lite-large-p2 model finetuned on IndoNLU(SmSA)

README.md

@@ -0,0 +1,24 @@
+---
+language: id
+tags:
+  - indobert
+  - indobenchmark
+  - indonlu
+license: mit
+inference: false
+datasets:
+  - Indo4B
+  - IndoNLU (SmSA)
+---
+
+# IndoBERT-Lite Large Model (phase2 - uncased) Finetuned on IndoNLU SmSA dataset
+
+## How to use
+
+### Load model and tokenizer
+
+```python
+from transformers import BertTokenizer, AutoModel
+tokenizer = BertTokenizer.from_pretrained("tyqiangz/indobert-lite-large-p2-smsa")
+model = AutoModel.from_pretrained("tyqiangz/indobert-lite-large-p2-smsa")
+```

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "indobenchmark/indobert-lite-large-p2",
+  "_num_labels": 5,
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 16,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 24,
+  "num_memory_blocks": 0,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05fb85c6421835bd1922fd0cc16d66e6450953ae5379fc2067858db559f84f1b
+size 70763217

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/root/.cache/huggingface/transformers/079b012b9db3ee4852c05e54afd77ca52783f176d619068fe301bdc3fdce319a.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_file": null, "name_or_path": "indobenchmark/indobert-lite-large-p2", "tokenizer_class": "BertTokenizer"}