Modelpublic

luel/nllb-200-distilled-600M-ft-en-efi

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face

0likes14downloads

Model Card

English - Efik (NLLB-200 Distilled)

Fine-tuned NLLB-200 model for translating English -> Efik. Efik is not directly supported in NLLB, we use the Igbo language code `ibo_Latn` as a close proxy during training and inference.

Usage

python

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

model_id = "luel/nllb-200-distilled-600M-ft-en-efi"

tokenizer = AutoTokenizer.from_pretrained(model_id, use_auth_token=True, src_lang="eng_Latn")
model = AutoModelForSeq2SeqLM.from_pretrained(model_id, use_auth_token=True)

input_example = "How are you?"
inputs = tokenizer(input_example, return_tensors="pt")

generated_ids = model.generate(
    **inputs, forced_bos_token_id = tokenizer.convert_tokens_to_ids("ibo_Latn"), max_length=30
)
print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0])

Training details (summary)

Item	Value
Base model	facebook/nllb-200-distilled-600M
Dataset	Davlan/ibom-mt-en-efi
Script	lafand-mt
Epochs	8
Effective batch size	32 (16 × 2 grad-accum)
Learning rate	3e-5
Mixed precision	bf16
Early stopping	Patience = 3, min_delta (BLEU) = 0.001

Evaluation

Metric	en->efi
BLEU	39.9
chrF	58.5

Limitations

—Using the Igbo token as a stand-in for Efik may introduce lexical differences.