ModelVerifiedExternal

Opus Mt Lt De Onnx Int8

Conversion movil-ready de Helsinki-NLP/opus-mt-lt-de . ONNX encoder model quantized.onnx decoder model quantized.onnx decoder with past model quantized.onnx (KV cache, decoding O(1) por token)

Verified source

Sourcehuggingface.co/R4kSo1997/opus-mt-lt-de-onnx-int8

KindtranslationVersionv5e4783597f371b2759d865f5094c85ad072cb982Publisher@R4kSo1997Cgrade

Model source

Kind: translation
Version: v5e4783597f371b2759d865f5094c85ad072cb982
Publisher: @R4kSo1997
Tasks: text-generation
Source: Hugging Face

Source description

--- library_name: transformers tags: - onnx - int8 - marian - opus-mt - translation - offline - lt - de --- # opus-mt-lt-de ONNX int8 (movil offline) Conversion movil-ready de `Helsinki-NLP/opus-mt-lt-de`. ## ONNX - encoder_model_quantized.onnx - decoder_model_quantized.onnx - decoder_with_past_model_quantized.onnx (KV cache, decoding O(1) por token) Quant: int8 dynamic ARM64 + per_channel. ## Tokenizer - tokenizer.json (Fast / Xenova / transformers.js) - source.spm, target.spm, vocab.json (Marian raw) Source: `Helsinki-NLP/opus-mt-lt-de` Repo: `R4kSo1997/opus-mt-lt-de-onnx-int8`

Sources & provenance

1 active source

Hugging FaceRepresentative

huggingface.co/R4kSo1997/opus-mt-lt-de-onnx-int8

highest_eligible_score

Verified Jul 11

Source evidence

3 excerpts

Readme excerptJul 11huggingface.co/R4kSo1997/opus-mt-lt-de-onnx-int8

decoderwithpastmodelquantized.onnx (KV cache, decoding O(1) por token)

SummaryJul 11huggingface.co/R4kSo1997/opus-mt-lt-de-onnx-int8