| test_stage: | |
| obcq_modifiers: | |
| SmoothQuantModifier: | |
| smoothing_strength: 0.8 | |
| mappings: [ | |
| [["re:.*q_proj", "re:.*k_proj", "re:.*v_proj"], "re:.*input_layernorm"], | |
| [["re:.*gate_proj", "re:.*up_proj"], "re:.*post_attention_layernorm"] | |
| ] | |
| QuantizationModifier: | |
| ignore: | |
| - LlamaRotaryEmbedding | |
| - LlamaRMSNorm | |
| - SiLUActivation | |
| post_oneshot_calibration: True | |
| scheme_overrides: | |
| Embedding: | |
| input_activations: null | |
| weights: | |
| num_bits: 8 | |
| symmetric: False | |
| SparseGPTModifier: | |
| sparsity: 0.0 | |
| block_size: 128 | |
| sequential_update: False | |
| quantize: True | |
| percdamp: 0.01 | |
| mask_structure: "0:0" | |
| targets: [ | |
| "re:model.layers.\\d*$" | |
| ] | |
| target_ids: ["attention_mask", "position_ids"] |