Downloads · 30 days
0
arrl-qwen3-4b-consilience-adapter
wheattoast11/arrl-qwen3-4b-consilience-adapter
arrl-qwen3-4b-consilience-adapter is a machine learning model from wheattoast11. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- Base model: sequelbox/Qwen3-4B-Thinking-2507-DAG-Reasoning - Adapters: LoRA adapters trained with ARRL (BNPO + EMA normalization, invariance, edge-of-chaos oscillators) - Usage (apply adapters to base model):
Access
Public
Updated Aug 13, 2025
Repo size
58.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors47.2 MB · 75%
At a glance
- Access
- Public
- Created
- Aug 13, 2025
- Updated
- Aug 13, 2025
- SHA
- 6f9715db
Model card
From the Hugging Face model README
ARRL Qwen3-4B Consilience (LoRA Adapters)
- Base model: sequelbox/Qwen3-4B-Thinking-2507-DAG-Reasoning
- Adapters: LoRA adapters trained with ARRL (BNPO + EMA normalization, invariance, edge-of-chaos oscillators)
- Usage (apply adapters to base model):
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = "sequelbox/Qwen3-4B-Thinking-2507-DAG-Reasoning"
adapter = "wheattoast11/arrl-qwen3-4b-consilience-adapter"
tok = AutoTokenizer.from_pretrained(base)
base_model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="auto", device_map="auto")
model = PeftModel.from_pretrained(base_model, adapter)
- Created
- Aug 13, 2025
- Updated
- Aug 13, 2025