| { | |
| "id": "ast_pruner", | |
| "name": "AST: Adaptive Semi-Structured 2:4 and N:M Pruning with Empirical Fisher Cal", | |
| "file": "Codes/framework/compression_engine/ast_pruner.py", | |
| "type": "Compression Engine", | |
| "category": "Low-Rank SVD & Factorization", | |
| "paradigm": "svd", | |
| "icon": "\u26a1", | |
| "description": "AST: Adaptive Semi-Structured 2:4 and N:M Pruning with Empirical Fisher Calibration and PCA Coordinate Rotation. Registered in COMPRESSOR_REGISTRY as 'ast_pruner' and 'ast'. Mathematical Formulation: 1. Activation Covariance & PCA Coordinate Rotation: $$\\Sigma_X = \\frac{1}{N - 1} (X - \\mu)^\\top (X - \\mu) = Q \\Lambda Q^\\top, \\quad Q^\\top Q = I$$ $$\\widetilde{W} = W Q, \\quad \\widetilde{X} = Q", | |
| "classes": [ | |
| "ASTPrunedLoRALinear", | |
| "ASTPruner" | |
| ], | |
| "methods_count": 12, | |
| "math_latex": "\\Sigma_X = Q \\Lambda Q^\\top, \\quad Q^\\top Q = I_{d_{\\text{in}}}", | |
| "components": [ | |
| { | |
| "id": "v_factor", | |
| "name": "Factor V (Low-Rank Subspace Projection)", | |
| "role": "Projection to Rank r", | |
| "shape_transform": "[r \u00d7 d_in]", | |
| "color": "#3acbb8", | |
| "math_latex": "z_t = x_t V_r^\\top, \\quad V_r \\in \\mathbb{R}^{r \\times d_{in}}" | |
| }, | |
| { | |
| "id": "u_factor", | |
| "name": "Factor U (Full-Rank Expansion Projection)", | |
| "role": "Expansion to Output Space", | |
| "shape_transform": "[d_out \u00d7 r]", | |
| "color": "#2dd4bf", | |
| "math_latex": "y_t = z_t (\\Sigma_r U_r^\\top) + b, \\quad U_r \\in \\mathbb{R}^{d_{out} \\times r}" | |
| }, | |
| { | |
| "id": "adapter", | |
| "name": "Residual LoRA / Norm Calibration", | |
| "role": "Fidelity Compensation", | |
| "shape_transform": "[d_out \u00d7 d_in] Residual", | |
| "color": "#5eead4", | |
| "math_latex": "\\Delta y_t = x_t (B A)^\\top \\cdot \\frac{\\alpha}{r}, \\quad A \\in \\mathbb{R}^{r \\times d_{in}}, \\; B \\in \\mathbb{R}^{d_{out} \\times r}" | |
| } | |
| ], | |
| "model_projections": { | |
| "distilbert": { | |
| "hidden_size": 768, | |
| "intermediate_size": 3072, | |
| "baseline_layer_params": 6488064, | |
| "compressed_layer_params": 786432, | |
| "savings_ratio": 8.25 | |
| }, | |
| "roberta": { | |
| "hidden_size": 768, | |
| "intermediate_size": 3072, | |
| "baseline_layer_params": 6488064, | |
| "compressed_layer_params": 786432, | |
| "savings_ratio": 8.25 | |
| }, | |
| "gpt2": { | |
| "hidden_size": 768, | |
| "intermediate_size": 3072, | |
| "baseline_layer_params": 6488064, | |
| "compressed_layer_params": 786432, | |
| "savings_ratio": 8.25 | |
| }, | |
| "qwen": { | |
| "hidden_size": 896, | |
| "intermediate_size": 4864, | |
| "baseline_layer_params": 11124736, | |
| "compressed_layer_params": 1081344, | |
| "savings_ratio": 10.29 | |
| } | |
| } | |
| } |
Xet Storage Details
- Size:
- 2.71 kB
- Xet hash:
- 102a8a95fff14710a69097ac17f3a7a4a30a965d105e9f697bc41f14a7707282
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.