# ======================================================
# 2️⃣ TOKENIZER
# ======================================================
PASHTO_ATOMS = ["ښ","څ","ځ","ڼ","ږ","ډ","ټ","ړ","ئ","ې","ۍ","ګ",
                "ک","ی","گ","چ","ژ","پ","ۀ","أ","إ","آ","ؤ","ء","ٱ",
                "ٹ","ڈ","ڑ","ں","ھ","ے","ۓ","۰","۱","۲","۳","۴","۵","۶","۷","۸","۹"]

Training Requirements

Continued Pretraining (CPT)

Requires large‑scale Pashto corpora, deduped and domain‑balanced.

Supervised Fine‑Tuning (SFT)

Requires high‑quality Pashto instruction datasets in chat format.

Thanks

Special thanks to the open‑source community and Pashto NLP contributors whose work made this model possible.

Citation

@article{liquidai2025lfm2,
  title={LFM2 Technical Report},
  author={Liquid AI},
  journal={arXiv preprint arXiv:2511.23404},
  year={2025}
}

📄 License

This model is released under the same license terms as the base model (LiquidAI/LFM2.5-1.2B-Base).
Please refer to the original model card for detailed license information.

nassimjp/LFM2.5-1.2B-Instruct-Pashto

2️⃣ TOKENIZER