TAO—Block—Subnets85 / 128active
No description set on the registered repo.
what the project says about itself — the input for semantic labels
No description set on the repo.
scope of the data
Taonets fetches the repo's public metadata (description, topics, language, stars, last push) and the head of its README. Commit-count histories, contributor lists and release notes require the GitHub commits/releases endpoints, which the worker doesn't consume yet — those panels are coming with the ingest upgrade and are not simulated in the meantime.
first lines of the default branch README, unedited
# Subnet 102 — Distributed Mixture-of-Experts Subnet 102 is a **Bittensor subnet** for collaborative, decentralized training of large language models using a Mixture-of-Experts (MoE) architecture. Miners train small residual experts beside a frozen base model (Qwen3.6-35B-A3B); validators score each miner's residual against the pretrained base, publish each round's best as the next round's starting point, and set weights that drive TAO rewards. ## Documentation For the most up-to-date and comprehensive documentation, including architecture overviews, setup guides for validators and miners, and reward optimization, please visit our official website: **[Connito AI](https://connito.ai/)** - [Running Your Miner](https://connito.ai/docs/miner) - [Running Your Validator](https://connito.ai/docs/validator) ## Contributing & License Contributions are welcome. Please open an issue first to discuss significant changes. See [LICENSE](LICENSE) for details.