lg → en Marian / Candle (Malinali)

Public on-device pack for Malinali: Helsinki-NLP OPUS-MT weights in safetensors form plus fast tokenizers for Candle (marian_flutter).

Upstream credit

Base model: Helsinki-NLP/opus-mt-lg-en
Project: Helsinki-NLP / OPUS-MT
License: follow the upstream model card (typically CC-BY 4.0 for OPUS-MT)

Malinali only repackages weights + converts SentencePiece → Hugging Face fast tokenizer JSON for on-device inference. We do not claim ownership of the trained model.

Files (required)

File	Role
`config.json`	Marian config
`model.safetensors`	Weights
`tokenizer-enc.json`	Source fast tokenizer
`tokenizer-dec.json`	Target fast tokenizer

Direction: lg → en.

Downloads last month: -

Safetensors

Model size

75.7M params

Tensor type

F32

Model tree for malinali-app/opus-mt-lg-en

Base model

Helsinki-NLP/opus-mt-lg-en

Finetuned

(8)

this model