Open Model Lab

Models

Model cards will document the models and checkpoints used in public evals before any model-quality claim is made.

Purpose

This page will track model identity, source, license, size, context length, quantization, checkpoints, intended eval use, and known limitations for public runs.

No model cards have been published yet.

Planned model categories

  • Base models
  • SFT checkpoints
  • DPO checkpoints
  • Agent-evaluated variants
  • Multimodal models if applicable later

Model card fields

  • model name
  • source
  • license
  • size
  • context length
  • quantization
  • adapter/checkpoint
  • intended eval use
  • known limitations
  • date added