AI is happening. The future is updating.pdmd_2NFE_lora
This repository holds the **LoRA adapter** of a 2-step (2 NFE) student distilled from MiniMax-H3 with **Projected Distribution Matching Distillation (PDMD)**. PDMD projects the DMD update onto the subspace orthogonal to the student–critic endpoint residual; it is a one-line change to DMD with no auxiliary loss, extra network, extra model pass, or extra training stage. The adapter is applied to the transformer (`MiniMaxH3Transformer3DModel`) of the base model. Every other component (VAE, audio VAE, schedulers, text encoder, processor) is unchanged and comes from the base model. Tensor keys have the form `transformer. .lora_A.weight` / `transformer. .lora_B.weight`, where ` .weight` is the corresponding parameter of `MiniMaxH3Transformer3DModel`. Fusing rule (also stored in the safetensors metadata):
This repository holds the **LoRA adapter** of a 2-step (2 NFE) student distilled from MiniMax-H3 with **Projected Distribution Matching Distillation (PDMD)**. PDMD projects the DMD update onto the subspace orthogonal to the student–critic endpoint residual; it is a one-line change to DMD with no auxiliary loss, extra network, extra model pass, or extra training stage. The adapter is applied to the transformer (`MiniMaxH3Transformer3DModel`) of the base model. Every other component (VAE, audio VAE, schedulers, text encoder, processor) is unchanged and comes from the base model. Tensor keys have the form `transformer. .lora_A.weight` / `transformer. .lora_B.weight`, where ` .weight` is the corresponding parameter of `MiniMaxH3Transformer3DModel`. Fusing rule (also stored in the safetensors metadata):