broadfield-dev/lora-adapters-qwen3-0.6b-r16-n180

LoRA Rule Adapters

Collection of 92 LoRA adapters trained on behavioral rules, one per rule. Used as ground-truth targets for hypernetwork training.

Base Model

Qwen/Qwen3-0.6B

Rule Types

Constraint, Format, Knowledge, Persona, Safety, Tone

Structure

Each subfolder is a self-contained PEFT adapter:

<rule_id>/
  adapter_config.json
  adapter_model.safetensors
  rule_metadata.json

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-0.6B")
model = PeftModel.from_pretrained(base, "//tone_0000")