encoder_model_quantized.onnx (int8 ARM64 dynamic, per-channel)
decoder_model_merged_quantized.onnx (int8 ARM64 dynamic, per-channel, merged: KV-cache + first-step)

Tokenizer

vocab.json, sentencepiece.bpe.model, tokenizer_config.json, special_tokens_map.json
tokenizer_data.json -> blob para Dart con vocab + scores + lang_tokens

Idiomas soportados

af, am, ar, ast, az, ba, be, bg, bn, br, bs, ca, ceb, cs, cy, da, de, el, en, es, et, fa, ff, fi, fr, fy, ga, gd, gl, gu, ha, he, hi, hr, ht, hu, hy, id, ig, ilo, is, it, ja, jv, ka, kk, km, kn, ko, lb, lg, ln, lo, lt, lv, mg, mk, ml, mn, mr, ms, my, ne, nl, no, ns, oc, or, pa, pl, ps, pt, ro, ru, sd, si, sk, sl, so, sq, sr, ss, su, sv, sw, ta, th, tl, tn, tr, uk, ur, uz, vi, wo, xh, yi, yo, zh, zu

Uso clave (importante)

SMaLL-100 funciona prepending el token del idioma DESTINO al input del encoder:

encoder_input  = [__<tgt_lang>__,  <texto_fuente_tokenizado>, </s>]
decoder_start  = </s>   (id=2)

Source: alirezamsh/small100 Target repo: R4kSo1997/small100-onnx-int8_v2