mirror of
https://github.com/vladmandic/automatic
synced 2026-09-01 10:01:01 +02:00
6ad67319de
Same parameterized shape as the core 4. - IA3: .on_input is the marker disambiguator (.weight is too generic). Fused targets skipped. - GLoRA: requires a1/a2/b1/b2 per group. Fused skipped (target-dependent term doesn't slice cleanly). - Norm: never fused. Loader-local network_layer_name stamping bypasses lora_convert's transformer-norm guard without changing the carve-out. - Full: fused skipped (no chunk class for diff tensors).