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
-
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