opus-mt-en-de machine translation (MarianMT)

Browser-ready import artifacts for translation, produced by SkillSafe's reproducible converter (models/ in skillsafe.ai) from a pinned upstream source. Every byte here is derivable from that source plus the recipe below; nothing was edited by hand.

Provenance

Upstream	https://huggingface.co/Xenova/opus-mt-en-de/tree/1ca130c44c4c5441ef16d48aae521a424ab644f7
Upstream SHA-256 / commit	1ca130c44c4c5441ef16d48aae521a424ab644f7
Recipe	recipes/opus-mt-en-de.yaml — sha256 486261838054ee6df3a38303ce6511c24438cd5ff35c13d1621e3e76d3b8c549
Toolchain	Python 3.12.13, torch 2.10.0, onnx 1.23.0, onnxruntime 1.30.0 on Darwin 25.6.0 arm64
Converted	2026-09-22T21:53:38+00:00

Files

file	class	size	SHA-256
config.json	bundle	0.00 MB	517955ebf66cd6523f9982851dd41771b74fb2d9c00b4933ba2922ac7a63336f
generation_config.json	bundle	0.00 MB	cd16a899388283889c6e87b903c689ce73430aaa18335415f9d9ea770606538e
onnx/decoder_model_merged.onnx	registry (fp32)	211.41 MB	bea9bca485118db5f5300bd1c77e8e07c9163215b9b5e1cf36d1e81b39cb57cb
onnx/decoder_model_merged_quantized.onnx	registry (q8)	54.03 MB	8b46a825964cdd182fe47cc780f0fb87d357eae1f47cf20aa63c1c09be5b510c
onnx/encoder_model.onnx	registry (fp32, q8)	186.74 MB	21bd75239e95412a523b993467781d902d4b14e86e49422ffabfe48e15ed3ca1
tokenizer.json	bundle	5.24 MB	8e0fcf45621ea87fa680c7f9969c37a7f819c1f4c7658a2e6e0879b866a14b17
tokenizer_config.json	bundle	0.00 MB	4500a1295197174119cf17f9b2e6eab2d5c3a9c64009fb1e37ebd2868bf1161c
vocab.json	bundle	1.33 MB	d5acea957b265a78554999144459c5e391e0df525864edc8287bc090290baa44

registry files are parameter files served from models.skillsafe.ai once vetted; bundle files ship inside an app; registry-shared is a runtime library reused by every model of the same architecture.

Verification

Imported as published upstream (no conversion). Each file is pinned by SHA-256 to its source; every ONNX file passed onnx.checker and a CPU smoke run under onnxruntime with zero-filled inputs at the declared shapes:

file	inputs	outputs	ms
onnx/decoder_model_merged.onnx	encoder_attention_mask[1, 8], input_ids[1, 4], encoder_hidden_states[1, 8, 512], past_key_values.0.decoder.key[1, 8, 1, 64], past_key_values.0.decoder.value[1, 8, 1, 64], past_key_values.0.encoder.key[1, 8, 8, 64], past_key_values.0.encoder.value[1, 8, 8, 64], past_key_values.1.decoder.key[1, 8, 1, 64], past_key_values.1.decoder.value[1, 8, 1, 64], past_key_values.1.encoder.key[1, 8, 8, 64], past_key_values.1.encoder.value[1, 8, 8, 64], past_key_values.2.decoder.key[1, 8, 1, 64], past_key_values.2.decoder.value[1, 8, 1, 64], past_key_values.2.encoder.key[1, 8, 8, 64], past_key_values.2.encoder.value[1, 8, 8, 64], past_key_values.3.decoder.key[1, 8, 1, 64], past_key_values.3.decoder.value[1, 8, 1, 64], past_key_values.3.encoder.key[1, 8, 8, 64], past_key_values.3.encoder.value[1, 8, 8, 64], past_key_values.4.decoder.key[1, 8, 1, 64], past_key_values.4.decoder.value[1, 8, 1, 64], past_key_values.4.encoder.key[1, 8, 8, 64], past_key_values.4.encoder.value[1, 8, 8, 64], past_key_values.5.decoder.key[1, 8, 1, 64], past_key_values.5.decoder.value[1, 8, 1, 64], past_key_values.5.encoder.key[1, 8, 8, 64], past_key_values.5.encoder.value[1, 8, 8, 64], use_cache_branch[1]	logits[1, 4, 58101], present.0.decoder.key[1, 8, 4, 64], present.0.decoder.value[1, 8, 4, 64], present.0.encoder.key[1, 8, 8, 64], present.0.encoder.value[1, 8, 8, 64], present.1.decoder.key[1, 8, 4, 64], present.1.decoder.value[1, 8, 4, 64], present.1.encoder.key[1, 8, 8, 64], present.1.encoder.value[1, 8, 8, 64], present.2.decoder.key[1, 8, 4, 64], present.2.decoder.value[1, 8, 4, 64], present.2.encoder.key[1, 8, 8, 64], present.2.encoder.value[1, 8, 8, 64], present.3.decoder.key[1, 8, 4, 64], present.3.decoder.value[1, 8, 4, 64], present.3.encoder.key[1, 8, 8, 64], present.3.encoder.value[1, 8, 8, 64], present.4.decoder.key[1, 8, 4, 64], present.4.decoder.value[1, 8, 4, 64], present.4.encoder.key[1, 8, 8, 64], present.4.encoder.value[1, 8, 8, 64], present.5.decoder.key[1, 8, 4, 64], present.5.decoder.value[1, 8, 4, 64], present.5.encoder.key[1, 8, 8, 64], present.5.encoder.value[1, 8, 8, 64]	5.5
onnx/decoder_model_merged_quantized.onnx	encoder_attention_mask[1, 8], input_ids[1, 4], encoder_hidden_states[1, 8, 512], past_key_values.0.decoder.key[1, 8, 1, 64], past_key_values.0.decoder.value[1, 8, 1, 64], past_key_values.0.encoder.key[1, 8, 8, 64], past_key_values.0.encoder.value[1, 8, 8, 64], past_key_values.1.decoder.key[1, 8, 1, 64], past_key_values.1.decoder.value[1, 8, 1, 64], past_key_values.1.encoder.key[1, 8, 8, 64], past_key_values.1.encoder.value[1, 8, 8, 64], past_key_values.2.decoder.key[1, 8, 1, 64], past_key_values.2.decoder.value[1, 8, 1, 64], past_key_values.2.encoder.key[1, 8, 8, 64], past_key_values.2.encoder.value[1, 8, 8, 64], past_key_values.3.decoder.key[1, 8, 1, 64], past_key_values.3.decoder.value[1, 8, 1, 64], past_key_values.3.encoder.key[1, 8, 8, 64], past_key_values.3.encoder.value[1, 8, 8, 64], past_key_values.4.decoder.key[1, 8, 1, 64], past_key_values.4.decoder.value[1, 8, 1, 64], past_key_values.4.encoder.key[1, 8, 8, 64], past_key_values.4.encoder.value[1, 8, 8, 64], past_key_values.5.decoder.key[1, 8, 1, 64], past_key_values.5.decoder.value[1, 8, 1, 64], past_key_values.5.encoder.key[1, 8, 8, 64], past_key_values.5.encoder.value[1, 8, 8, 64], use_cache_branch[1]	logits[1, 4, 58101], present.0.decoder.key[1, 8, 4, 64], present.0.decoder.value[1, 8, 4, 64], present.0.encoder.key[1, 8, 8, 64], present.0.encoder.value[1, 8, 8, 64], present.1.decoder.key[1, 8, 4, 64], present.1.decoder.value[1, 8, 4, 64], present.1.encoder.key[1, 8, 8, 64], present.1.encoder.value[1, 8, 8, 64], present.2.decoder.key[1, 8, 4, 64], present.2.decoder.value[1, 8, 4, 64], present.2.encoder.key[1, 8, 8, 64], present.2.encoder.value[1, 8, 8, 64], present.3.decoder.key[1, 8, 4, 64], present.3.decoder.value[1, 8, 4, 64], present.3.encoder.key[1, 8, 8, 64], present.3.encoder.value[1, 8, 8, 64], present.4.decoder.key[1, 8, 4, 64], present.4.decoder.value[1, 8, 4, 64], present.4.encoder.key[1, 8, 8, 64], present.4.encoder.value[1, 8, 8, 64], present.5.decoder.key[1, 8, 4, 64], present.5.decoder.value[1, 8, 4, 64], present.5.encoder.key[1, 8, 8, 64], present.5.encoder.value[1, 8, 8, 64]	6.0
onnx/encoder_model.onnx	input_ids[1, 8], attention_mask[1, 8]	last_hidden_state[1, 8, 512]	1.4

Use in the browser

import * as ort from "onnxruntime-web";
const session = await ort.InferenceSession.create("https://huggingface.co/skillsafe-ai/opus-mt-en-de/resolve/main/onnx/decoder_model_merged.onnx", { executionProviders: ["webgpu", "wasm"] });

Contract (onnx/decoder_model_merged.onnx): input encoder_attention_mask int64 ['batch_size', 'encoder_sequence_length'], input_ids int64 ['batch_size', 'decoder_sequence_length'], encoder_hidden_states float32 ['batch_size', 'encoder_sequence_length', 512], past_key_values.0.decoder.key float32 ['batch_size', 8, 'past_decoder_sequence_length', 64], past_key_values.0.decoder.value float32 ['batch_size', 8, 'past_decoder_sequence_length', 64], past_key_values.0.encoder.key float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], past_key_values.0.encoder.value float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], past_key_values.1.decoder.key float32 ['batch_size', 8, 'past_decoder_sequence_length', 64], past_key_values.1.decoder.value float32 ['batch_size', 8, 'past_decoder_sequence_length', 64], past_key_values.1.encoder.key float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], past_key_values.1.encoder.value float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], past_key_values.2.decoder.key float32 ['batch_size', 8, 'past_decoder_sequence_length', 64], past_key_values.2.decoder.value float32 ['batch_size', 8, 'past_decoder_sequence_length', 64], past_key_values.2.encoder.key float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], past_key_values.2.encoder.value float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], past_key_values.3.decoder.key float32 ['batch_size', 8, 'past_decoder_sequence_length', 64], past_key_values.3.decoder.value float32 ['batch_size', 8, 'past_decoder_sequence_length', 64], past_key_values.3.encoder.key float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], past_key_values.3.encoder.value float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], past_key_values.4.decoder.key float32 ['batch_size', 8, 'past_decoder_sequence_length', 64], past_key_values.4.decoder.value float32 ['batch_size', 8, 'past_decoder_sequence_length', 64], past_key_values.4.encoder.key float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], past_key_values.4.encoder.value float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], past_key_values.5.decoder.key float32 ['batch_size', 8, 'past_decoder_sequence_length', 64], past_key_values.5.decoder.value float32 ['batch_size', 8, 'past_decoder_sequence_length', 64], past_key_values.5.encoder.key float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], past_key_values.5.encoder.value float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], use_cache_branch bool [1] → output logits float32 ['batch_size', 'decoder_sequence_length', 58101], present.0.decoder.key float32 ['batch_size', 8, 'past_decoder_sequence_length + 1', 64], present.0.decoder.value float32 ['batch_size', 8, 'past_decoder_sequence_length + 1', 64], present.0.encoder.key float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], present.0.encoder.value float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], present.1.decoder.key float32 ['batch_size', 8, 'past_decoder_sequence_length + 1', 64], present.1.decoder.value float32 ['batch_size', 8, 'past_decoder_sequence_length + 1', 64], present.1.encoder.key float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], present.1.encoder.value float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], present.2.decoder.key float32 ['batch_size', 8, 'past_decoder_sequence_length + 1', 64], present.2.decoder.value float32 ['batch_size', 8, 'past_decoder_sequence_length + 1', 64], present.2.encoder.key float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], present.2.encoder.value float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], present.3.decoder.key float32 ['batch_size', 8, 'past_decoder_sequence_length + 1', 64], present.3.decoder.value float32 ['batch_size', 8, 'past_decoder_sequence_length + 1', 64], present.3.encoder.key float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], present.3.encoder.value float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], present.4.decoder.key float32 ['batch_size', 8, 'past_decoder_sequence_length + 1', 64], present.4.decoder.value float32 ['batch_size', 8, 'past_decoder_sequence_length + 1', 64], present.4.encoder.key float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], present.4.encoder.value float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], present.5.decoder.key float32 ['batch_size', 8, 'past_decoder_sequence_length + 1', 64], present.5.decoder.value float32 ['batch_size', 8, 'past_decoder_sequence_length + 1', 64], present.5.encoder.key float32 ['batch_size', 8, 'encoder_sequence_length_out', 64], present.5.encoder.value float32 ['batch_size', 8, 'encoder_sequence_length_out', 64]. Opset 11.

Licence and attribution

opus-mt-en-de: Helsinki-NLP (Jörg Tiedemann, University of Helsinki), CC-BY-4.0, trained on OPUS data (https://huggingface.co/Helsinki-NLP/opus-mt-en-de); ONNX export by Xenova (https://huggingface.co/Xenova/opus-mt-en-de).

Licence: CC-BY-4.0 — notice: https://huggingface.co/Helsinki-NLP/opus-mt-en-de/blob/main/README.md. The conversion recipe and this model card are part of the SkillSafe repository and carry its licence; the weights remain under the upstream licence above.

The full manifest.json in this repo records the recipe, sources, toolchain (including the uv.lock hash) and per-file verification numbers.