SPB Git

spb/forge Public MIT

Forge — LLM training from scratch in pure C++20 + Metal on Apple Silicon.

C++ 61.2% C 23% Python 7.6% TeX 7.2% CMake 1.1%
NameLast commitUpdated
forge-tiny-25m-smoke.json chore: commit pending workspace changes yesterday
gpt-100m.json Forge: LLM training from scratch in C++20 + Metal on Apple Silicon 10 days ago
gpt-10m-1epoch.json Forge: LLM training from scratch in C++20 + Metal on Apple Silicon 10 days ago
gpt-10m.json Forge: LLM training from scratch in C++20 + Metal on Apple Silicon 10 days ago
gpt-200m-cluster.json 200M cluster run: one epoch at micro-batch 8 10 days ago
gpt-200m.json Forge: LLM training from scratch in C++20 + Metal on Apple Silicon 10 days ago
gpt-25m.json Forge: LLM training from scratch in C++20 + Metal on Apple Silicon 10 days ago
gpt-50m-deep.json Add configurable training modes: Muon optimizer and WSD schedule 5 days ago
gpt-50m-gemma.json Add architecture-variant waves 1+2: train... 5 days ago
gpt-50m-mistral.json Add architecture-variant waves 1+2: train... 5 days ago
gpt-50m-moe.json Add QAT, MoE, and architecture-variant knobs — all config-selected 5 days ago
gpt-50m-muon.json Add configurable training modes: Muon optimizer and WSD schedule 5 days ago
gpt-50m-ternary.json Add QAT, MoE, and architecture-variant knobs — all config-selected 5 days ago
gpt-50m.json Add configurable training modes: Muon optimizer and WSD schedule 5 days ago
gpt-smoke.json Forge: LLM training from scratch in C++20 + Metal on Apple Silicon 10 days ago
richard-10m-1epoch.json chore: commit pending workspace changes yesterday