dv-muril

README.md

@@ -0,0 +1,21 @@
+---
+language: dv
+---
+
+# dv-muril
+
+This is an experiment in transfer learning, to insert Dhivehi word and
+word-piece tokens into Google's MuRIL model.
+
+This BERT-based model currently performs better than dv-wave ELECTRA on
+the Maldivian News Classification task https://github.com/Sofwath/DhivehiDatasets
+
+## Training
+
+- Start with MuRIL (similar to mBERT) with no Thaana vocabulary
+- Based on PanLex dictionaries, attach 1,100 Dhivehi words to Malayalam or English embeddings
+- Add remaining words and word-pieces from dv-wave to vocab.txt
+- Continue BERT pretraining on a TPU
+
+CoLab notebook: 
+https://colab.research.google.com/drive/1kPyd60EtOFLaHRVToNS-IKj29T9JCvMq?usp=sharing

config.json

@@ -0,0 +1,22 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 768,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "type_vocab_size": 2,
+  "vocab_size": 225175
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a73c8b0f83fd28c74dca57854d254453e5ea4b948e07ae980eb56febfe6a2c0b
+size 1036895067

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": false, "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": false, "lowercase": false, "special_tokens_map_file": "/root/.cache/huggingface/transformers/d66e90c2d485729cd831f5a30ce5724c25dcfbff7055265820652f3277c1412e.750293617705dd39d21eef1e163d80ca5b23e1a0ec507fff24a087c44632142c", "tokenizer_file": null, "name_or_path": "./dvadd"}