| { | |
| "base_model": "Roblox/cubepart", | |
| "library": "torchao", | |
| "torchao_version": "0.11.0", | |
| "torch_version": "2.8.0+cu128", | |
| "method": "HQQ", | |
| "scheme": "W4A16", | |
| "config": "int4_weight_only(group_size=128, use_hqq=True)", | |
| "group_size": 128, | |
| "quantized_scope": "nn.Linear layers in transformer_blocks and multi_transformer_blocks of diffusion_model", | |
| "skipped_name_substrings": [ | |
| "img_in", | |
| "txt_in", | |
| "proj_out", | |
| "pos_embed", | |
| "time_text_embed", | |
| "norm" | |
| ], | |
| "untouched_modules": [ | |
| "shape_model", | |
| "base_model.text_encoder" | |
| ], | |
| "checkpoint_file": "multi_part_dit_int4_hqq_g128.pt", | |
| "checkpoint_file_safetensors": "multi_part_dit_int4_hqq_g128.safetensors", | |
| "checkpoint_contents": "diffusion_model.state_dict() after in place quantization", | |
| "load_recipe": "instantiate the pipeline, quantize_ diffusion_model with the same config and filter, then load_state_dict with defaults (no assign=True), weights_only=False", | |
| "load_recipe_safetensors": "instantiate the pipeline, quantize_ diffusion_model with the same config and filter, flatten each state_dict tensor via __tensor_flatten__ into '<key>::<inner>' leaves, then copy_ each leaf from the file (see README)", | |
| "required_env": { | |
| "TORCHDYNAMO_DISABLE": "1" | |
| } | |
| } | |