---
library_name: peft
base_model: Qwen/Qwen3-8B
license: apache-2.0
tags:
  - electronics
  - embedded-systems
  - embedded
  - lora
  - sft
  - ailiance-tuning
language:
  - en
  - fr
datasets:
  - custom
pipeline_tag: text-generation
---

# Ailiance EMBEDDED SFT — LoRA Adapter

Fine-tuned LoRA adapter for **embedded** domain expertise, based on `Qwen/Qwen3-8B`.

Part of the [Ailiance Models Tuning](https://github.com/ailiance/ailiance-models-tuning) pipeline
for the [Ailiance](https://github.com/ailiance) platform.

## Training Details

| Parameter | Value |
|-----------|-------|
| Base Model | `Qwen/Qwen3-8B` |
| Method | QLoRA (4-bit NF4) |
| LoRA Rank | 16 |
| Epochs | 3 |
| Dataset | 8344 examples |
| Domain | embedded |

## Usage

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

model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B", device_map="auto")
model = PeftModel.from_pretrained(model, "clemsail/ailiance-embedded-sft")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B")
```

## License

Apache 2.0

## 🇪🇺 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 | Ailiance (clemsail / electron-rare) |
| Role under AI Act | GPAI provider for this adapter |
| Base model | `Qwen/Qwen3-8B` — see upstream provenance |
| Adapter type | LoRA / PEFT — adapter weights only; base unchanged |
| Training data origin | Ailiance proprietary technical corpus + curated public docs |
| License | Apache-2.0 (adapter). Upstream base licence applies separately. |
| Intended use | Embedded systems programming |
| 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.