| { |
| "add_skip_keys": false, |
| "dequantize_fp32": false, |
| "dynamic_loss_threshold": null, |
| "group_size": 0, |
| "hadamard_group_size": 128, |
| "is_integer": true, |
| "is_training": false, |
| "modules_dtype_dict": {}, |
| "modules_quant_config": {}, |
| "modules_to_not_convert": [ |
| "encoder.down.0.block.0.norm1.weight", |
| "encoder.down.0.block.0.norm2.weight", |
| "encoder.down.0.block.1.norm1.weight", |
| "encoder.down.0.block.1.norm2.weight", |
| "encoder.down.1.block.0.norm1.weight", |
| "encoder.down.1.block.0.norm2.weight", |
| "encoder.down.1.block.1.norm1.weight", |
| "encoder.down.1.block.1.norm2.weight", |
| "encoder.down.2.block.0.norm1.weight", |
| "encoder.down.2.block.0.norm2.weight", |
| "encoder.down.2.block.1.norm1.weight", |
| "encoder.down.2.block.1.norm2.weight", |
| "encoder.down.3.block.0.norm1.weight", |
| "encoder.down.3.block.0.norm2.weight", |
| "encoder.down.3.block.1.norm1.weight", |
| "encoder.down.3.block.1.norm2.weight", |
| "encoder.mid.block_1.norm1.weight", |
| "encoder.mid.block_1.norm2.weight", |
| "encoder.mid.attn_1.norm.weight", |
| "encoder.mid.block_2.norm1.weight", |
| "encoder.mid.block_2.norm2.weight", |
| "encoder.norm_out.weight", |
| "decoder.mid.block_1.norm1.weight", |
| "decoder.mid.block_1.norm2.weight", |
| "decoder.mid.attn_1.norm.weight", |
| "decoder.mid.block_2.norm1.weight", |
| "decoder.mid.block_2.norm2.weight", |
| "decoder.up.0.block.0.norm1.weight", |
| "decoder.up.0.block.0.norm2.weight", |
| "decoder.up.0.block.1.norm1.weight", |
| "decoder.up.0.block.1.norm2.weight", |
| "decoder.up.0.block.2.norm1.weight", |
| "decoder.up.0.block.2.norm2.weight", |
| "decoder.up.1.block.0.norm1.weight", |
| "decoder.up.1.block.0.norm2.weight", |
| "decoder.up.1.block.1.norm1.weight", |
| "decoder.up.1.block.1.norm2.weight", |
| "decoder.up.1.block.2.norm1.weight", |
| "decoder.up.1.block.2.norm2.weight", |
| "decoder.up.2.block.0.norm1.weight", |
| "decoder.up.2.block.0.norm2.weight", |
| "decoder.up.2.block.1.norm1.weight", |
| "decoder.up.2.block.1.norm2.weight", |
| "decoder.up.2.block.2.norm1.weight", |
| "decoder.up.2.block.2.norm2.weight", |
| "decoder.up.3.block.0.norm1.weight", |
| "decoder.up.3.block.0.norm2.weight", |
| "decoder.up.3.block.1.norm1.weight", |
| "decoder.up.3.block.1.norm2.weight", |
| "decoder.up.3.block.2.norm1.weight", |
| "decoder.up.3.block.2.norm2.weight", |
| "decoder.norm_out.weight" |
| ], |
| "modules_to_not_use_matmul": [], |
| "non_blocking": false, |
| "quant_conv": true, |
| "quant_embedding": false, |
| "quant_method": "sdnq", |
| "quantization_device": "cuda", |
| "quantized_matmul_dtype": null, |
| "return_device": "cpu", |
| "sdnq_version": "0.1.9", |
| "svd_rank": 32, |
| "svd_steps": 8, |
| "use_dynamic_quantization": false, |
| "use_grad_ckpt": true, |
| "use_hadamard": false, |
| "use_quantized_matmul": false, |
| "use_quantized_matmul_conv": false, |
| "use_static_quantization": true, |
| "use_stochastic_rounding": false, |
| "use_svd": false, |
| "weights_dtype": "uint4" |
| } |
|
|
