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.

>>> 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

BibTex entry and Citation info

coming soon ...