Platform
Private AI infrastructure — from compute to agents.
Target groups
For enterprise, SMBs, and individual developers.
Knowledge & Support
Everything you need to succeed with Mycelis.
Intelligence
Specialize open-source models for your domain. Upload your own training data, configure hyperparameters, and deploy the finished model directly in the Mycelis ecosystem.
What is LoRA fine-tuning?
LoRA (Low-Rank Adaptation) is an efficient fine-tuning method that adjusts only a small subset of model weights instead of retraining all parameters. Result: 90% less GPU memory than full fine-tuning with comparable quality.
LoRA adapters are stored as small additional weights (~10–100 MB) and combined with the base model at deployment time.
When is fine-tuning worth it?
Medicine, law, engineering — the model learns domain-specific terms and relationships.
Company tone in output: formal, casual, technical — the model writes like your team.
Classification, extraction, structuring — higher precision for specific tasks.
Optimize for specific languages, regional phrasing, or internal naming conventions.
Step-by-step process
JSONL format: {"prompt": "...", "completion": "..."}. At least 50–200 examples for good results. We recommend 500–2000.
Upload to the knowledge base or directly as a training file. Supported formats: JSONL, CSV.
Choose base model (e.g. Llama 3.1 8B), learning rate, epochs, and LoRA rank (r=8 is a good starting point).
Mycelis automatically starts an A100 80GB GPU instance for training. Billing is based on GPU hours.
Review sample outputs in the dashboard. If satisfied, deploy directly as a deployment — done.
Training costs
| Model | GPU | Training time (500 examples) |
|---|---|---|
| Llama 3.1 8B | RTX 4090 (€0.39/h) | ~2–4 hrs → €0.78–€1.56 |
| Llama 3.1 70B | A100 80GB (€1.99/h) | ~6–12 hrs → €11.94–€23.88 |
| Mistral 7B | RTX 4090 (€0.39/h) | ~1.5–3 hrs → €0.59–€1.17 |
Estimated values for LoRA fine-tuning. Actual duration depends on data volume and hyperparameters.
Frequently asked questions
Training starts from ~€1 for small models. No minimum, no base fee.
Start fine-tuning now