LoRA Fine-Tuning with Axolotl

Specific fine-tuning implementation using LoRA rank 32, learning rate 2e-4, AdamW 8-bit optimizer

Neighborhood — ranked by edge-count

method

LoRA Fine-Tuning
related_to
Adaptation method used via Tinker API for DeepSeek-V3.1 and Qwen3-235B fine-tuning with rank 32
LoRA
implements
Low-rank adaptation method used for SFT.

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

rs-LoRA Finetuningmethod0.767
Low-rank adaptation method used for finetuning models in all experiments; rank 32, alpha 64
A LoRA adapter can learn to add a constant vector equivalent to steering along a pre-existing persona direction, making fine-tuning literally equivalent to activation steeringclaim0.748
Mechanistic explanation of how fine-tuning can shift persona vectors without directly updating activations
Fine-tuningconcept0.726
Parameter updates that reduce mismatch dr; another anchoring variant in UCCT.
Low-Rank Adaptation (LoRA)method0.724
Parameter-efficient fine-tuning method used to implement SOO fine-tuning on LLMs
Can targeted fine-tuning reverse RP suppression, given that LoRA caps both baseline and latent capacity?question0.723
Practical intervention question arising from RP suppression finding
LoRA (Low-Rank Adaptation)method0.721
Parameter-efficient fine-tuning method used for both SDF and expert iteration stages.
Fine Tuning and Adaptationconcept0.719
The patient, hand-guided adjustment of shape and dimension to each unique condition in a building; requires materials that make it economical and easy.
LoRA: Low-Rank Adaptation of Large Language Models (Hu et al., 2022)concept0.718
Fine-tuning method paper whose technique is used in the fine-tuning experiments