KIKI KiCad SFT v1
Fine-tuned QLoRA adapter for KiCad/EDA electronic design.
- Base: Qwen/Qwen2.5-7B, Method: QLoRA 4-bit NF4
- Dataset: 22 KiCad examples (USB routing, DRC, Gerber, DFM, zones, SPICE, footprints)
- Loss: 1.535, Accuracy: 67.1%, GPU: RTX 4090, Time: 25s
🇪🇺 EU AI Act transparency
This adapter is provided as a fine-tuned LoRA under the AI Act framework (Regulation EU 2024/1689). Compliance metadata:
| Field | Value |
|---|---|
| Provider | L'Électron Rare (clemsail / electron-rare) |
| Role under AI Act | GPAI provider for this adapter |
| Base model | Qwen/Qwen2.5-7B — see upstream provenance |
| Adapter type | LoRA / PEFT — adapter weights only; base unchanged |
| Training data origin | L'Électron Rare proprietary technical corpus + curated public docs |
| License | Apache-2.0 (adapter). Upstream base licence applies separately. |
| Intended use | KiCad PCB design assistance |
| Out of scope | Healthcare diagnosis, legal advice, autonomous safety-critical decisions, generation of malicious code |
| Risk classification | Limited risk — Article 50 transparency obligations apply |
| Copyright respect | Training data does not include scraped copyrighted material. Opt-out signals (robots.txt, ai.txt) are honoured for web-sourced data. |
| Full provenance | https://github.com/ailiance/ailiance/tree/main/docs/provenance |
| Contact | postmaster@saillant.cc — biased output reports, copyright concerns, etc. |
⚠️ You are using an AI model. Outputs may be inaccurate, biased or fabricated. Do not act on them without independent verification, especially in regulated domains.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for electron-rare/kiki-kicad-sft-v1
Base model
Qwen/Qwen2.5-7B