commit from dronny

README.md

@@ -1 +1,8 @@
-Pretrained Roberta on Dagaare language textual data.
+---
+datasets:
+- Bible
+---
+
+Pretrained model on Dagaare language using a masked language modeling (MLM) objective first introduced in 
+[this paper](https://arxiv.org/abs/1907.11692) and first released in
+[this repository](https://github.com/pytorch/fairseq/tree/master/examples/roberta)\

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0405a19cb2ff74d238ed533281280428c4cba03ffe70d0948f382971733faae9
+size 498861675

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ac621e169cdbefb1416bded046d446e21da94a8c9e5b6b16de329491a6e32d
+size 429302640

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}