| { | |
| "per_block_num_heads": [ | |
| 12, | |
| 12, | |
| 12, | |
| 11, | |
| 11, | |
| 12, | |
| 11, | |
| 11, | |
| 12, | |
| 9, | |
| 11, | |
| 10 | |
| ], | |
| "per_block_kept_heads": { | |
| "0": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11 | |
| ], | |
| "1": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11 | |
| ], | |
| "2": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11 | |
| ], | |
| "3": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11 | |
| ], | |
| "4": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 9, | |
| 10, | |
| 11 | |
| ], | |
| "5": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11 | |
| ], | |
| "6": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 10, | |
| 11 | |
| ], | |
| "7": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10 | |
| ], | |
| "8": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11 | |
| ], | |
| "9": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8 | |
| ], | |
| "10": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11 | |
| ], | |
| "11": [ | |
| 0, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 10, | |
| 11 | |
| ] | |
| }, | |
| "per_block_removed_heads": { | |
| "0": [], | |
| "1": [], | |
| "2": [], | |
| "3": [ | |
| 5 | |
| ], | |
| "4": [ | |
| 8 | |
| ], | |
| "5": [], | |
| "6": [ | |
| 9 | |
| ], | |
| "7": [ | |
| 11 | |
| ], | |
| "8": [], | |
| "9": [ | |
| 11, | |
| 10, | |
| 9 | |
| ], | |
| "10": [ | |
| 4 | |
| ], | |
| "11": [ | |
| 1, | |
| 9 | |
| ] | |
| }, | |
| "head_dim": 64, | |
| "dim": 768 | |
| } |