How to use from the
Use from the
Transformers library
# Use a pipeline as a high-level helper
# Warning: Pipeline type "translation" is no longer supported in transformers v5.
# You must load the model directly (see below) or downgrade to v4.x with:
# 'pip install "transformers<5.0.0'
from transformers import pipeline

pipe = pipeline("translation", model="cle-13/nllb-tooro-ttj-patched")
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("cle-13/nllb-tooro-ttj-patched")
model = AutoModelForSeq2SeqLM.from_pretrained("cle-13/nllb-tooro-ttj-patched", device_map="auto")
Quick Links

NLLB-200 Rutooro (ttj_Latn) โ€” patched

A patched copy of cle-13/nllb-tooro enabling ttj_Latn (warm-started from lug_Latn) so that downstream adapters can decode with forced_bos_token_id=ttj_Latn.

Downloads last month
12
Safetensors
Model size
0.6B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for cle-13/nllb-tooro-ttj-patched

Finetuned
(1)
this model
Adapters
1 model