---
license: apache-2.0
base_model:
- Qwen/Qwen3.6-27B
datasets:
- microsoft/SchGen_dataset
language:
- en
library_name: peft
tags:
- pcb
- eda
- kicad
- schematic-generation
- schgen
- lora
- qwen3
---

# SchGen-Qwen3.6-27B-EU — LoRA adapter

PEFT/LoRA adapter for KiCad schematic generation, to be applied on top of
[`Qwen/Qwen3.6-27B`](https://huggingface.co/Qwen/Qwen3.6-27B) (Apache-2.0).
This is the **adapter only** (~152 MB); for the merged model see
[`Ailiance-fr/SchGen-Qwen3.6-27B-EU`](https://huggingface.co/Ailiance-fr/SchGen-Qwen3.6-27B-EU).

Implements the SchGen method ([Luo et al., 2026](https://arxiv.org/abs/2605.30345))
on a sovereign EU stack by [ailiance](https://huggingface.co/Ailiance-fr).

## Config

LoRA rank 32, α 1024, dropout 0.01, targets `q/k/v/o/gate/up/down` on the top
16 layers (48–63), curriculum (3 phases) over
[`microsoft/SchGen_dataset`](https://huggingface.co/datasets/microsoft/SchGen_dataset) (MIT).

## Usage

```python
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.6-27B", torch_dtype="bfloat16", device_map="auto")
model = PeftModel.from_pretrained(base, "Ailiance-fr/SchGen-Qwen3.6-27B-EU-lora")
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3.6-27B")
```

See the [merged model card](https://huggingface.co/Ailiance-fr/SchGen-Qwen3.6-27B-EU)
for evaluation, limitations, and citation.

## License

Apache-2.0. Derivative of `Qwen/Qwen3.6-27B` (Apache-2.0), trained on
`microsoft/SchGen_dataset` (MIT). See `NOTICE`.