2026-10-11 16:36 UTC

lora

band: coolmomentum: stable score: 0.002
temperature history

Episodes (2)

Independent reproduction will determine whether the published GGUF-based workflow can LoRA-train Qwen3.6-35B-A3B within 16GB of VRAM using APEX quantization and fused kernels without prohibitive performance or quality tradeoffs.
expiredknownscott: medium
The paper’s author claims constraining fine-tuning to subspaces learned from trusted LoRA adapters can block malicious model updates while preserving useful adaptation, potentially adding a geometric defense against fine-tuning poisoning.
expiredconvergesscott: medium

Trajectory notes