adding Naija BERT

README.md

@@ -0,0 +1,40 @@
+Hugging Face's logo
+---
+language: pcm
+datasets:
+
+---
+# bert-base-multilingual-cased-finetuned-naija
+## Model description
+**bert-base-multilingual-cased-finetuned-naija** is a **Nigerian-Pidgin BERT** model obtained by fine-tuning **bert-base-multilingual-cased** model on Nigerian-Pidgin language texts.  It provides **better performance** than the multilingual BERT on named entity recognition datasets.  
+
+Specifically, this model is a *bert-base-multilingual-cased* model that was fine-tuned on Nigerian-Pidgin 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-naija')
+>>> unmasker("Another attack on ambulance happen for Koforidua in March [MASK] year where robbers kill Ambulance driver")
+
+```
+#### 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 JW300 + [BBC Pidgin](https://www.bbc.com/pidgin)
+
+## Training procedure
+This model was trained on a single NVIDIA V100 GPU
+
+## Eval results on Test set (F-score, average over 5 runs)
+Dataset| mBERT F1 | pcm_bert F1
+-|-|-
+[MasakhaNER](https://github.com/masakhane-io/masakhane-ner) | 87.23 | 89.95
+
+### BibTeX entry and citation info
+By David Adelani
+```
+
+```
+
+

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "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 sha256:87cac1c45d2aef859af09e5f2ad9cfae2989f92f176eb4c1b6df7b1337483a6f
+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:fc2f5bc84e8108e26c93b7c3e2218d83eb32ca7317060aa94ce6ef1c7d4b0de3
+size 2287