FROM THE CREATOR OF GLINER
Describe the task and let the Fastino agent generates high-quality data, runs full or LoRA training, and automated evals. All from your coding agent.
HOW THE AGENT WORKS
01
Research the task and objectives
The agent starts researching and scoping the project based on your supplied tasks and objectives.
02
Source or generate synthetic data
Once training plan is approved, the agent sources, generate high-quality synthetic data, or curates supplied datasets.
03
Run experiments & evaluations
The agent can perform LoRA sweeps or full fine-tunes, and automated evals with provenance receipts.
04
Ship the checkpoint
Deploy the endpoint for inference, or push the checkpoint to your Hugging Face space.
The agent cli
Agent to agent. Claude Code, Codex, or Cursor hands the task to the Fastino agent, which trains your model in hours and returns the checkpoint, training data, and eval report.
claude code · ~/acme/support-graph
› use the Fastino agent to train a GLiNER knowledge-graph extractor on ./data/tickets/*.jsonl
I will hand this to the Fastino agent over A2A and stream its run back here.
A2A call · fastino.train
task: knowledge_graph
base_model: gliner-2.5
corpus: ./data/tickets/*.jsonl
eval: ./evals/graph_holdout.jsonl
budget: lora_then_full · max_hours: 8
fastino · run kg-7f3a accepted · streaming
Proposed the graph schema
11 node types, 7 edge types, confirmed against your taxonomy
Generated and filtered training data
128k synthetic triples reduced to 61k after dedupe and span checks
Ran 9 LoRA sweeps, promoted the winner to a full fine-tune
node F1 0.91 · edge F1 0.84 · +14 over zero-shot
Deployed and pushed the checkpoint
POST /v1/gliner-2.5-kg/extract · fastino/GLiNER-2.5-KnowledgeGraph
run complete in 7h 12m. checkpoint, training data, and eval report written to ./fastino/kg-7f3a/
› now wire it into the ingest pipeline
Same loop, MULTIPLE tasks
LLM guardrails
Injection, policy, topic checks.
PII detection
Span-accurate redaction.
Model routing
Cheapest model that clears the bar.
Knowledge graphs
Nodes, edges, JSON triples.
Classification
Hundreds of classes.
Structured extraction
Any document to typed JSON.
Fine-tune GLiNER models and make it your own
The autonomous agent that built the GLiNER family of models is now available in private preview.
Get access