LoRA adapter fine-tuning Qwen/Qwen2.5-Coder-1.5B-Instruct into an assistant for the Nodrix ESP32/Arduino library. Trained in Unsloth Studio (MLX, Apple Silicon). LoRA r=16, alpha=16, all linear modules, seq 512, 3 epochs / 63 steps, 167 training examples.

First smoke run. Fixed form (real C++, prose-vs-code routing) but not facts. No eval set attached.

Load

python

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = "Qwen/Qwen2.5-Coder-1.5B-Instruct"
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base)
model = PeftModel.from_pretrained(model, "decoded-cipher/nodrix-coder-1.5b-lora-v1")

System prompt used in training:

You are the Nodrix build assistant. You help ESP32 and Arduino developers build projects with the Nodrix library. Use only real Nodrix APIs.

License: Apache-2.0 (inherited from the base model).