| { | |
| "module_name": "cachenotes_compressor", | |
| "class_name": "CacheNotesCompressor", | |
| "category": "compression", | |
| "family": "compression", | |
| "params": [ | |
| "max_cache_len", | |
| "task_type", | |
| "keep_ratio", | |
| "num_sinks", | |
| "model", | |
| "recalibrate_ln", | |
| "tokenizer", | |
| "calibration_loader", | |
| "calibration_texts", | |
| "device" | |
| ], | |
| "ops": [ | |
| "linear", | |
| "matmul", | |
| "norm", | |
| "softmax" | |
| ], | |
| "docstring": "CacheNotes Compressor: Decouples static weight compression from KV cache dynamic pruning.\nCompresses static model weights using CPT-guided low-rank SVD without zeroing out entire output channels.\n\nArgs:\n model: PyTorch model.\n task_type: Target downstream task ('qa', 'summarize', 'code', 'reasoning', 'math').\n keep_ratio: Fraction of rank / energy to retain (default 0.5).\n recalibrate_ln: Whether to recalibrate LayerNorm statistics after compression.", | |
| "rank": 16, | |
| "d_state": 1, | |
| "num_experts": 1, | |
| "top_k": 1, | |
| "sparsity_pct": 0.0, | |
| "bits": 4, | |
| "hash_val": 259550964849013102013658601722562170684 | |
| } |
Xet Storage Details
- Size:
- 1.07 kB
- Xet hash:
- d1f9ed66c29113b25d0a86b5bce3fdf356d736e92098e84fd463fa1db71325fb
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.