How it works
From dataset to deployed adapter
A guided pipeline with a checkpoint you control before every training run.
- 1
Upload
Add a JSONL dataset of examples.
- 2
Validate
Automatic format and length checks.
- 3
Synthesize
Optional teacher-generated examples.
- 4
Train
LoRA on your chosen base model.
- 5
Evaluate
Perplexity and exact-match metrics.
- 6
Deploy
Serve the adapter behind an endpoint.
What you get
Custom models, no ops
Everything needed to specialize an open model and serve it in production.
LoRA fine-tuning
Configure rank and alpha, and train adapters on base models like Qwen 2.5 7B, Qwen 3.5 35B-A3B, Llama 3.1 8B, and Gemma 4 31B.
Bring your own data — or synthesize it
Upload a JSONL dataset, or generate training examples from an open teacher model (DeepSeek-R1, Qwen3, GLM-4.5, Kimi K2) and review them before training.
Pay per minute
Billed for actual GPU training time. Failed validation or generation isn't charged.
Multi-LoRA serving
Deploy many adapters on a single inference instance without restarts.
BYOK with KMS encryption
Bring your own teacher API key — it's sealed with KMS envelope encryption and never stored in plaintext.
Evaluation metrics
Get perplexity and exact-match metrics for every run.