Hugging Face's logo
---
language: 
- om
- am
- rw
- rn
- ha
- ig
- pcm
- so
- sw
- ti
- yo
- multilingual
tags:
- T5

---
# afriteva_large

## Model desription

AfriTeVa large is a sequence to sequence model pretrained on 10 African languages

## Languages

Afaan Oromoo(orm), Amharic(amh), Gahuza(gah), Hausa(hau), Igbo(igb), Nigerian Pidgin(pcm), Somali(som), Swahili(swa), Tigrinya(tig), Yoruba(yor)

### More information on the model, dataset:

### The model

- 745M parameters encoder-decoder architecture (T5-like)
- 12 layers, 12 attention heads and 512 token sequence length

### The dataset

- Multilingual: 10 African languages listed above
- 143 Million Tokens (1GB of text data)
- Tokenizer Vocabulary Size: 70,000 tokens

## Intended uses & limitations 

`afriteva_large` is pre-trained model and primarily aimed at being fine-tuned on multilingual sequence-to-sequence tasks. 

```python
>>> from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

>>> tokenizer = AutoTokenizer.from_pretrained("castorini/afriteva_large")
>>> model = AutoModelForSeq2SeqLM.from_pretrained("castorini/afriteva_large")

>>> src_text = "Ó hùn ọ́ láti di ara wa bí?"
>>> tgt_text =  "Would you like to be?"

>>> model_inputs = tokenizer(src_text, return_tensors="pt")
>>> with tokenizer.as_target_tokenizer():
        labels = tokenizer(tgt_text, return_tensors="pt").input_ids

>>> model(**model_inputs, labels=labels) # forward pass
```

## Training Procedure

For information on training procedures, please refer to the AfriTeVa [paper](#) or [repository](https://github.com/castorini/afriteva)

## BibTex entry and Citation info

coming soon ...