Guide
What Hermes Agent is, steps to set up, how it compares to other agents, and how to use it with Pioneer.
Research
Guide
What OpenCode is, how to set it up, how it compares to other agents, and how to run any model via Pioneer.
Guide
An overview of what inference is and what affects inference speed and performance.
Guide
An overview of how to choose the best frontier and open-source coding models for the right tasks.
Guide
A practical guide to SLMs: main architectures, when they outperform frontier models on production tasks, and how to fine-tune one.
Engineering
Our serving path falls off a cliff at adapter 33. Here's why, and what we did about it.
Research
Research
Research
The research behind Pioneer, where fine-tuning small language models becomes a closed loop.
Product
We’re launching Pioneer, the world’s first agent for fine-tuning and inferencing open source SLMs and LLMs.
Research
The future belongs to models with architectures crafted, optimized, and deployed for focused tasks.
Research
The one-size-fits-all LLM era is over. Scaling AI effectively now demands matching models to the right domain or task.
Correcting Stochastic Update Bias in Preconditioned Language Model Optimizers
GLiNER2-PII: A Multilingual Model for Personally Identifiable Information Extraction
GLiGuard: Schema-Conditioned Classification for LLM Content Moderation
Pioneer Agent: Continual Improvement of Small Language Models in Production
GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer
GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface
Beyond Reactivity: Measuring Proactive Problem solving in LLM Agents
