adding Hausa BERT

README.md

@@ -0,0 +1,58 @@
+Hugging Face's logo
+---
+language: yo
+datasets:
+
+---
+# bert-base-multilingual-cased-finetuned-yoruba
+## Model description
+**bert-base-multilingual-cased-finetuned-yoruba** is a **Yoruba BERT** model obtained by fine-tuning **bert-base-multilingual-cased** model on Yorùbá language texts.  It provides **better performance** than the multilingual BERT on text classification and named entity recognition datasets.  
+
+Specifically, this model is a *bert-base-multilingual-cased* model that was fine-tuned on Yorùbá corpus. 
+## Intended uses & limitations
+#### How to use
+You can use this model with Transformers *pipeline* for masked token prediction.
+```python
+>>> from transformers import pipeline
+>>> unmasker = pipeline('fill-mask', model='Davlan/bert-base-multilingual-cased-finetuned-yoruba')
+>>> unmasker("Arẹmọ Phillip to jẹ ọkọ [MASK] Elizabeth to ti wa lori aisan ti dagbere faye lẹni ọdun mọkandilọgọrun")
+
+[{'sequence': '[CLS] Arẹmọ Phillip to jẹ ọkọ Mary Elizabeth to ti wa lori aisan ti dagbere faye lẹni ọdun mọkandilọgọrun [SEP]', 'score': 0.1738305538892746, 
+'token': 12176, 
+'token_str': 'Mary'}, 
+{'sequence': '[CLS] Arẹmọ Phillip to jẹ ọkọ Queen Elizabeth to ti wa lori aisan ti dagbere faye lẹni ọdun mọkandilọgọrun [SEP]', 'score': 0.16382873058319092, 
+'token': 13704, 
+'token_str': 'Queen'}, 
+{'sequence': '[CLS] Arẹmọ Phillip to jẹ ọkọ ti Elizabeth to ti wa lori aisan ti dagbere faye lẹni ọdun mọkandilọgọrun [SEP]', 'score': 0.13272495567798615, 
+'token': 14382, 
+'token_str': 'ti'}, 
+{'sequence': '[CLS] Arẹmọ Phillip to jẹ ọkọ King Elizabeth to ti wa lori aisan ti dagbere faye lẹni ọdun mọkandilọgọrun [SEP]', 'score': 0.12823280692100525, 
+'token': 11515, 
+'token_str': 'King'}, 
+{'sequence': '[CLS] Arẹmọ Phillip to jẹ ọkọ Lady Elizabeth to ti wa lori aisan ti dagbere faye lẹni ọdun mọkandilọgọrun [SEP]', 'score': 0.07841219753026962, 
+'token': 14005, 
+'token_str': 'Lady'}]
+
+```
+#### Limitations and bias
+This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains. 
+## Training data
+This model was fine-tuned on Bible, JW300, [Menyo-20k](https://huggingface.co/datasets/menyo20k_mt), [Yoruba Embedding corpus](https://huggingface.co/datasets/yoruba_text_c3) and [CC-Aligned](https://opus.nlpl.eu/), Wikipedia, news corpora (BBC Yoruba, VON Yoruba, Asejere, Alaroye), and other small datasets curated from friends.
+
+## Training procedure
+This model was trained on a single NVIDIA V100 GPU
+
+## Eval results on Test set (F-score)
+Dataset|F1-score
+-|-
+Yoruba GV NER |75.34
+MasakhaNER |80.82
+BBC Yoruba |80.66
+
+### BibTeX entry and citation info
+By David Adelani
+```
+
+```
+
+

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "hau_bert/checkpoint-200000",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "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,
+  "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",
+  "transformers_version": "4.4.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc4868ac260b22c68a5cd4368c98ff089bab954797f6829eaff9e6f03cd80cad
+size 711988242

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, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-multilingual-cased"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb2fc5750e5ebf61ba7614dfb6cecaf5d66c130ba8978770279f682fdc7eb348
+size 2287