Llama-3.2-1B-MTP-k8
This is a reproduction of «Multi-Token Prediction via Self-Distillation» (arXiv 2602.06019) adapted for a single NVIDIA RTX 5090...
This is a reproduction of «Multi-Token Prediction via Self-Distillation» (arXiv 2602.06019) adapted for a single NVIDIA RTX 5090...