ProjectNeura/varest_weights/methods/learnpruner/llava-1.5-13b - Storage Bucket

LearnPruner LPM. The trained LPM is BUDGET-INDEPENDENT: the training mask is argmax over the LPM's own scores, so the retention budget never enters training and is applied at inference. Verified bitwise -- the four LLaVA-1.5-7B runs, the four 13B runs, and three NeXT runs at different ratios each produced identical weights. Use this single checkpoint for every ratio (0.0556 / 0.1111 / 0.2222 / 0.3889). Trained on LLaVA-Tuning/llava_v1_5_mix665k.json, subset_frac 0.10, seed 2026, 1 epoch, 62,441 examples. This backbone: model_max_length 1024 (2048 OOMs on one 80GB H100).