MathIR parser LoRA v2 (E4c)

Base: Qwen2.5-7B-Instruct. Train: mathir-synth-hu revision v2 (accepted families plus ambiguous / insufficient_information / contradictory / unsupported). Eval: frozen gold only.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support