---
language:
  - nl
  - zh
tags:
  - causal-lm
  - language-model
  - babylm
  - babylm-2026
  - multilingual
  - gpt2
  - paradigmfinder
pipeline_tag: text-generation
library_name: transformers
---

# gpt2_parfind_nl_zh_equal

Bilingual GPT-2 model packaged for the BabyLM 2026 multilingual evaluation track.

Source experiment: `/home/achille.fusco/pr_baby_lm/BabyLM_2026_ENH/04-experiments/model_gpt2_ParFindFast_nld_zho_BD_budget16k_zhchildes_v1.0`

Hugging Face target repo: `NeTSlab/gpt2_parfind_nl_zh_equal`

Current status on July 6, 2026: `resume_needed`

Notes:
- `main` is intended to point to the final 1000M checkpoint (`epoch_9`).
- The custom ParadigmFinder tokenizer is bundled with the model files.
- Loading from HF requires `trust_remote_code=True`.