| { | |
| "batcher": null, | |
| "cacher": null, | |
| "compiler": null, | |
| "distiller": null, | |
| "distributer": null, | |
| "enhancer": null, | |
| "factorizer": null, | |
| "kernel": null, | |
| "pruner": null, | |
| "quantizer": "hqq", | |
| "recoverer": null, | |
| "hqq_backend": "torchao_int4", | |
| "hqq_compute_dtype": "torch.bfloat16", | |
| "hqq_force_hf_implementation": true, | |
| "hqq_group_size": 64, | |
| "hqq_use_torchao_kernels": false, | |
| "hqq_weight_bits": 4, | |
| "batch_size": 1, | |
| "device": "cuda", | |
| "device_map": null, | |
| "save_fns": [], | |
| "load_fns": [ | |
| "transformers" | |
| ], | |
| "reapply_after_load": { | |
| "factorizer": null, | |
| "pruner": null, | |
| "quantizer": null, | |
| "distiller": null, | |
| "kernel": null, | |
| "cacher": null, | |
| "recoverer": null, | |
| "distributer": null, | |
| "compiler": null, | |
| "batcher": null, | |
| "enhancer": null | |
| } | |
| } |