inference-optimization/dflash-DeepSeek-V4-Flash-all-swa-muon-speculators-50k

Remove partial_rotary_factor (no-op: trainer uses full rotary)

Upload README.md with huggingface_hub

Upload val_metrics.json with huggingface_hub

Upload config.py with huggingface_hub

Upload config.json with huggingface_hub

Upload model.safetensors with huggingface_hub

initial commit