Downloads · 30 days
0
lora-adapters-qwen3-0.6b-r16-n180
broadfield-dev/lora-adapters-qwen3-0.6b-r16-n180
lora-adapters-qwen3-0.6b-r16-n180 is a machine learning model from broadfield-dev. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
Collection of 92 LoRA adapters trained on behavioral rules, one per rule. Used as ground-truth targets for hypernetwork training.
Access
Public
Updated Mar 1, 2026
Repo size
1.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.7 GB · 100%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Feb 28, 2026
- Updated
- Mar 1, 2026
- SHA
- a78b9ded
Base models
Model card
From the Hugging Face model README
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")
- Library
- peft
- License
- apache-2.0
- Created
- Feb 28, 2026
- Updated
- Mar 1, 2026