Instructions to use StarlexAI/Orbit-Nano-Compliance-E2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use StarlexAI/Orbit-Nano-Compliance-E2B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="StarlexAI/Orbit-Nano-Compliance-E2B", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("StarlexAI/Orbit-Nano-Compliance-E2B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use StarlexAI/Orbit-Nano-Compliance-E2B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "StarlexAI/Orbit-Nano-Compliance-E2B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "StarlexAI/Orbit-Nano-Compliance-E2B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/StarlexAI/Orbit-Nano-Compliance-E2B
- SGLang
How to use StarlexAI/Orbit-Nano-Compliance-E2B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "StarlexAI/Orbit-Nano-Compliance-E2B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "StarlexAI/Orbit-Nano-Compliance-E2B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "StarlexAI/Orbit-Nano-Compliance-E2B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "StarlexAI/Orbit-Nano-Compliance-E2B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use StarlexAI/Orbit-Nano-Compliance-E2B with Docker Model Runner:
docker model run hf.co/StarlexAI/Orbit-Nano-Compliance-E2B
Orbit-Nano-Compliance-E2B
A German and English compliance model, pretrained from scratch by Starlex AI on about 1 % of the data that comparable small models see, and the best of seven models on our EU and German compliance benchmark.
| Pretraining data | 92.4B tokens (Llama 3.2 9T, Qwen3 36T) |
| Pretraining time | 30.8 hours on one node with 8 GPUs, about 380 kWh |
| Parameters | 4.03B total, compute of a 1.75B model per token |
| Languages | German and English |
| Focus | GDPR, NIS-2, EU AI Act, IT-Grundschutz, German federal law |
| License | Apache-2.0 |
Results
Starlex Compliance-Bench DE v2
4,582 questions on 1,200 passages of German and EU law, held out of all training data. The questions were written by Mistral Large 3 and checked by GLM-5.3. Every model is scored the same way.
| Model | Lab | Score | Closed book |
|---|---|---|---|
| Orbit-Nano-Compliance-E2B | Starlex AI | 68.5, rank 1 of 7 | 59.4 |
| Ministral | Mistral AI | below 68.5 | 48.9 |
If the benchmark leans towards any model family, it leans towards Mistral, because Mistral Large 3 wrote the questions. Ministral still finishes behind Orbit-Nano.
Public benchmarks
| Orbit-Nano | Ministral | |
|---|---|---|
| German benchmark average | 43.5 (rank 2) | 49.2 |
| MMLU | near chance |
General world knowledge is where training data pays off, and Orbit-Nano has seen very little of it. That is the gap the next, larger training run is meant to close.
Safety and grounding
| Result | |
|---|---|
| Refuses harmful requests, German (25 prompts) | 100 % |
| Refuses harmful requests, English (10 prompts) | 30 % |
| Refuses compliance misuse (e.g. hiding a data breach) | 9 of 10 |
| Wrong answers on German law, without / with retrieved provisions | 72 % / 45 % |
Safety is judged by GLM-5.3 on our own prompt sets (judge noise about 2 to 3 points). With the actual provisions in the prompt, the error rate drops by more than a third, so use Orbit-Nano with retrieval.
Try it
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("StarlexAI/Orbit-Nano-Compliance-E2B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("StarlexAI/Orbit-Nano-Compliance-E2B", trust_remote_code=True, dtype="bfloat16")
msgs = [{"role": "user", "content": "Welche Meldepflichten gelten nach Art. 33 DSGVO?"}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt")
print(tok.decode(model.generate(ids, max_new_tokens=400)[0, ids.shape[1]:], skip_special_tokens=True))
Runs on a laptop with the GGUF files in StarlexAI/Orbit-Nano-Compliance-E2B-GGUF (Q4_K_M is 2.4 GB).
How it was built
Everything below was done by Starlex AI, from random weights to this release.
- Tokenizer. Own BPE tokenizer with 65,536 tokens, trained on German and English text.
- Data. FineWeb-Edu, FineWeb2-HQ German, FinePDFs German with a regulatory subset, German Wikipedia, FineMath, German federal law and EU law in German, plus synthetic compliance texts and German rephrasings generated locally with GLM-5.3. Only sources whose licenses allow an Apache-2.0 release.
- Pretraining. 92.4B tokens at 835,000 tokens per second, Muon for the matrices and AdamW for embeddings.
- Chat and compliance fine tuning. Two rounds of supervised fine tuning. Round 2.1 adds about 4,000 safety pairs (harmful versus benign requests).
- Release checks. Every quantization is tested against bf16 before it ships.
Architecture
- nanochat architecture: 32 layers, d 2048, 16 heads, RoPE, QK-norm, ReLU² MLP, value embeddings, smear gate, x0 and residual lambdas, backout, logit softcap 15
- E2B means about 2B effective parameters: 2.15B of the 4.03B are value embeddings that are only looked up
- Context length 2,048 tokens
- The export rescales the MLP weights by an exact power of two (up / 8, down x 64). Outputs are unchanged, and large internal activations stay inside the range of 16-bit formats.
Limitations
- Small model. It hallucinates, especially exact article numbers, dates and case law. Use it with retrieval of the actual provisions and check every legal statement. Not legal advice.
- English safety is weak. German is the stronger language.
- Context 2,048 tokens. F16 GGUF does not work (bf16, Q8_0, Q5_K_M and Q4_K_M are verified).
- Custom architecture, so transformers needs
trust_remote_code=Trueand GGUF needs llama.cpp with theorbitarchitecture.
The Orbit family
| Model | What it does |
|---|---|
| Orbit-Nano-Compliance-E2B | German and English compliance chat |
| Orbit Phone | Speech recognition, 2.60 % WER on LibriSpeech test-clean |
| Orbit-Vision | Questions about images, charts and documents (research preview) |
| Orbit-Image | Pixel art from text (research preview) |
Built by Starlex AI, a Foundation AI Lab.
- Downloads last month
- 14
