initial commit

README.md

@@ -0,0 +1,57 @@
+Hugging Face's logo
+---
+language: 
+- om
+- am
+- rw
+- rn
+- ha
+- ig
+- pcm
+- so
+- sw
+- ti
+- yo
+- multilingual
+
+---
+# afriberta_large
+## Model description
+AfriBERTa large is a pretrained multilingual language model with around 126 million parameters.
+The model has 10 layers, 6 attention heads, 768 hidden units and 3072 feed forward size.
+The model was pretrained on 11 African languages namely - Afaan Oromoo (also called Oromo), Amharic, Gahuza (a mixed language containing Kinyarwanda and Kirundi), Hausa, Igbo, Nigerian Pidgin, Somali, Swahili, Tigrinya and Yorùbá.
+The model has been shown to obtain competitive downstream performances on text classification and Named Entity Recognition on several African languages, including those it was not pretrained on. 
+
+
+## Intended uses & limitations
+
+#### How to use
+You can use this model with Transformers for any downstream task. 
+For example, assuming we want to finetune this model on a token classification task, we do the following:
+
+```python
+>>> from transformers import AutoTokenizer, AutoModelForTokenClassification
+>>> model = AutoModelForTokenClassification.from_pretrained("castorini/afriberta_large")
+>>> tokenizer = AutoTokenizer.from_pretrained("castorini/afriberta_large")
+# we have to manually set the model max length because it is an imported sentencepiece model, which huggingface does not properly support right now
+>>> tokenizer.model_max_length = 512 
+```
+
+#### Limitations and bias
+- This model is possibly limited by its training dataset which are majorly obtained from news articles from a specific span of time. Thus, it may not generalize well.
+
+
+## Training data
+The model was trained on an aggregation of datasets from the BBC news website and Common Crawl. 
+
+## Training procedure
+For information on training procedures, please refer to the AfriBERTa [paper]() or [repository](https://github.com/keleog/afriberta)
+
+### BibTeX entry and citation info
+```
+Kelechi Ogueji, Yuxin Zhu, Jimmy Lin.
+Small Data? No Problem! Exploring the Viability of Pretrained Multilingual Language Models for Low-resourced Languages
+Proceedings of the 1st workshop on Multilingual Representation Learning at EMNLP 2021
+```
+
+

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/Users/kelechogueji/Downloads/afriberta_large",
+  "architectures": [
+    "XLMRobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "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-05,
+  "max_length": 512,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 10,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.2.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 70006
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d0a3c04de0206b6ec857cb19f320eb1c8737c67c4b4cd5cb56fd7b64c5d277b
+size 502885341

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6419b3044bff45e94e0553cbb81425fd06046e9294b33555e23fdc69377dba6f
+size 1554839

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": "<mask>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "spm_models/spm_model_final_70k"}