🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
- bloom
- deep-learning
- distributed-systems
- language-models
47,133 repositories indexed
1–4 of 4 · Most stars
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
Better judgment. Better taste. Less ceremony. System instructions and source-aware steering for GPT in Codex.
Wrap Gemini CLI as an OpenAI-compatible API service, allowing you to enjoy the free Gemini Pro model through API!