--- datasets: - colesimmons/SumTablets base_model: - Qwen/Qwen3-VL-8B-Instruct pipeline_tag: translation tags: - Sumerian, - Cuneiform --- Hang tight. 6/1/2026: Training is done and this is a much more capable model than Gemma4-E4B. After the training it had very deep understanding, but had a issue where the EoF was blurred because of a training setting (minor issue). This caused a couple of similar signs to be confused, but very strong understanding overall. I most likely will retrain it in the next day or two, and while that is being fixed here are the Q4, Q5, Q6 and Q8 for this version. Yes.. Gemma4-E4B will also benifit from the EoF blur that was caught, and i will lower the LR to deepen its understanding which will make it far more capable. 🍻