Downloads · 30 days
0
small100-onnx-int8
PEWTER/small100-onnx-int8
small100-onnx-int8 is a translation model from PEWTER. Use it when you need text moved from one language to another. The card lists the license as apache-2.0.
Self-exported INT8 ONNX of alirezamsh/small100 (distilled M2M-100, Apache-2.0) for on-device CPU inference (onnxruntime). Non-merged encoder/decoder. General model — NOT a ja/vi fine-tune.
Access
Public
Updated Jun 6, 2026
Repo size
605 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx605 MB · 99%
At a glance
- Task
- Translation
- License
- apache-2.0
- Access
- Public
- Created
- Jun 6, 2026
- Updated
- Jun 6, 2026
- SHA
- 4bdedf1a
Model card
From the Hugging Face model README
SMaLL-100 — INT8 ONNX (general, 100 languages)
Self-exported INT8 ONNX of alirezamsh/small100 (distilled M2M-100, Apache-2.0) for on-device CPU inference (onnxruntime). Non-merged encoder/decoder. General model — NOT a ja/vi fine-tune.
encoder.onnx: input_ids, attention_mask -> last_hidden_statedecoder.onnx: input_ids, encoder_attention_mask, encoder_hidden_states -> logitstokenizer.json: m2m100_418M tokenizer (same vocab as small100)
Scheme: encoder input = [tgt_lang_id, ...sp_pieces, eos=2]; decode greedily from eos=2 (no forced bos).
- Task
- Translation
- License
- apache-2.0
- Languages
- multilingual
- Created
- Jun 6, 2026
- Updated
- Jun 6, 2026