Yeco Flash Mini-IT v1
118M-parameter Italian micro-LLM, trained for under €15, ~200 tok/s on CPU. Beats 5× larger models on Italian logic benchmarks.
Proprietary 3B model trained on EnderDevelopment data. In beta, rolling out on EnderDevelopment.
Ender-1 is our proprietary 3B-parameter model purpose-built for the gaming ecosystem: Minecraft (Spigot/Paper) plugins, FiveM scripts, Discord bots, and server configuration (YAML/JSON, BungeeCord/Velocity). It powers the EnderDevelopment generation pipeline.
Trained on EnderDevelopment data — free-tier users, strictly within platform policy. The corpus covers natural-language feature requests, accepted outputs, compile results, and community-vetted configurations. No private or paid-tier data is used.
As rollout proceeds, acceptance signals from real deployments feed the next training cycle — the same compact-model, rigorous-evaluation methodology proven with Yeco-PII.
118M-parameter Italian micro-LLM, trained for under €15, ~200 tok/s on CPU. Beats 5× larger models on Italian logic benchmarks.
Proprietary 278M model. Beats OpenAI Privacy Filter 1.5B (F1 0.966 vs 0.769) on all 6 languages.
Mechanics of prompt injection and sandbox testing for defenses.