R.O.A.D. Barbados Historic Handwriting Challenge
'/%3e%3c/svg%3e)
Helping Barbados
$25 000 USD
Closing soon! (13 days left)
Optical Character Recognition
Natural Language Processing
1740 joined
574 active
Start
03 Jul 26
Close
04 Oct 26
Reveal
04 Oct 26
Licence approval request — stanford-oval/churro-3B (Qwen Research licence)
19 Aug 2026, 01:38 · 4
Hi @meganomaly,
On 5 Aug you said models under research-only or non-commercial licences need reviewing before use, and asked entrants to post the model name and a licence link. Doing that here as a new thread, as the original has gone quiet.
Model: stanford-oval/churro-3B Licence: Qwen Research License Agreement (non-commercial) https://huggingface.co/stanford-oval/churro-3B/blob/main/LICENSE Public weights, not gated.
Is it acceptable for this challenge? If it's acceptable with conditions, please say which and I'll include them in my final documentation. This is blocking which model family I build on for the rest of the competition, so any indication of timing would help. Thanks.
Thanks for raising this, and for sharing the model and licence details so clearly.
After reviewing the licence, stanford-oval/churro-3B would unfortunately not be permitted for this challenge under its current Qwen Research License. The licence restricts use to non-commercial purposes, while solutions developed through this challenge may need to be used or deployed by the challenge partner beyond research or evaluation.
To avoid creating downstream licensing restrictions for the final solution, please use a model whose licence permits commercial use. If a separate commercial licence for this model is available and obtained, we’d be happy to review that separately.
Thanks again for checking before proceeding.
Hi @meganomaly,
I’d like to request approval to use the PP-OCRv6 Medium historical HTR model for this challenge.
Model: PP-OCRv6 Medium Licence: Apache-2.0 Model card: https://zenodo.org/records/21788410
I would like to use this model in my competition solution. Please inspect the model, its licence, and any relevant training-data licences as you see appropriate and let me know whether it is permitted for the challenge.
Thank you.
Hi @MuhammadQasimShabbear Thanks for the query. Based on the official model repository, the PP-OCRv6 medium model and PP-OCRv6 medium recognition weights can be used commercially under Apache 2.0, making it fine to use.
Thanks for reply also there was other query to use https://zenodo.org/records/248733 this dataset for domain adaption of vlm it is same type of data opensource or should we only use this competition dataset