Text Generation
MLX
English
French
lora
mlx-lm
qwen3.5
Mixture of Experts
spice
ngspice
electronics
micro-kiki
hypneum-lab
Instructions to use hypneum-lab/micro-kiki-stack-spice with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use hypneum-lab/micro-kiki-stack-spice with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("hypneum-lab/micro-kiki-stack-spice") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use hypneum-lab/micro-kiki-stack-spice with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "hypneum-lab/micro-kiki-stack-spice" --prompt "Once upon a time"
- Atomic Chat
docs: AI Act transparency
Browse files
README.md
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# micro-kiki-stack-spice
|
| 2 |
+
|
| 3 |
+
## 🇪🇺 EU AI Act transparency
|
| 4 |
+
|
| 5 |
+
This artefact is published under the AI Act framework (Regulation EU 2024/1689).
|
| 6 |
+
|
| 7 |
+
| Field | Value |
|
| 8 |
+
|---|---|
|
| 9 |
+
| Provider | L'Électron Rare (clemsail) |
|
| 10 |
+
| Role under AI Act | GPAI provider |
|
| 11 |
+
| Adapter type | MLX merged adapter — SPICE simulation specialty |
|
| 12 |
+
| Base model | `Qwen/Qwen3.5-35B-A3B (via micro-kiki v3 LoRA stack)` |
|
| 13 |
+
| License | Apache-2.0 |
|
| 14 |
+
| Intended use | SPICE / NGSPICE / LTspice circuit simulation assistance |
|
| 15 |
+
| Out of scope | Healthcare diagnosis, legal advice, autonomous safety-critical decisions |
|
| 16 |
+
| Risk classification | Limited risk — Article 50 transparency obligations apply |
|
| 17 |
+
| Copyright respect | Training data does not include scraped copyrighted material |
|
| 18 |
+
| Full provenance | https://github.com/L-electron-Rare/eu-kiki/tree/main/docs/provenance |
|
| 19 |
+
| Contact | postmaster@saillant.cc |
|
| 20 |
+
|
| 21 |
+
⚠️ **You are using an AI model.** Outputs may be inaccurate, biased or
|
| 22 |
+
fabricated. Do not act on them without independent verification, especially
|
| 23 |
+
in regulated domains.
|
| 24 |
+
|
| 25 |
+
|