saejon/MinimaxH3

Based on the original Minimax H3 BF16 model, it was merged with the LoRA at a weight of 1.0.

ComfyOrg Model Tool was used.

To make it exactly identical to the official Minimax H3 model, Block 0 and Block 1 were not quantized.

The file size and quantization structure are identical to the official model.

공식 BF16 기반으로 1.0가중치로 병합됨, COMFYui 공식툴 사용함, 공식 모델과 동일하게 0번, 1번 블록은 양자화하지 않음.

Lightx2v 공식 Lora가 사용되었으며 Kijai Lora는 사용되지 않았음.