method
active
method:loraLoRA
Low-rank adaptation method used for SFT.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (2)
method
- Synthetic Self-Correction Fine-TuningimplementsFine-tuning on Claude-generated self-correction examples with loss masking to induce ESR-like behavior
- LoRA Fine-Tuning with AxolotlimplementsSpecific fine-tuning implementation using LoRA rank 32, learning rate 2e-4, AdamW 8-bit optimizer