XueFuzhao/OpenMoE resource

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1695 stars · 86 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

OpenMoE is a family of open-sourced Mixture-of-Experts (MoE) large language models, including base and chat variants at 8B scale, released with training data, code, and model weights. It is a student-led research project aimed at growing the open-source MoE community and includes routing analysis research.

Use cases

• run an open-source mixture-of-experts LLM
• study MoE routing behavior in large language models
• fine-tune or continue training an open MoE model
• convert JAX checkpoints to PyTorch
• research sparse expert models without closed weights

When to choose

• you want fully open MoE weights, data, and training details for research
• you want to experiment with or extend an open MoE LLM
• you need a reproducible academic baseline for MoE LLM studies

When to avoid

• you need a production-grade, actively maintained LLM with commercial support
• you require a permissive license for commercial use (no license is specified)
• you want the strongest possible model performance rather than research transparency

Facets

learning-resource · maturity maintenance

llm-training machine-learning deep-learning large-language-models machine-learning artificial-intelligence python cloud mixture-of-experts open-source-models jax pytorch research-project model-weights gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="XueFuzhao/OpenMoE")