| { | |
| "model_type": "gpt_oss", | |
| "original_num_experts": 32, | |
| "num_experts_per_tok": 4, | |
| "dropped_experts_per_layer": { | |
| "0": [ | |
| 0, | |
| 4, | |
| 5, | |
| 12, | |
| 14, | |
| 15, | |
| 18, | |
| 19, | |
| 20, | |
| 21, | |
| 29, | |
| 30, | |
| 31 | |
| ], | |
| "1": [ | |
| 3, | |
| 4, | |
| 5, | |
| 7, | |
| 8, | |
| 9, | |
| 14, | |
| 19, | |
| 21, | |
| 23, | |
| 24, | |
| 25, | |
| 31 | |
| ], | |
| "2": [ | |
| 1, | |
| 2, | |
| 7, | |
| 9, | |
| 11, | |
| 12, | |
| 13, | |
| 14, | |
| 15, | |
| 16, | |
| 17, | |
| 18, | |
| 19, | |
| 26, | |
| 30 | |
| ], | |
| "3": [ | |
| 4, | |
| 5, | |
| 6, | |
| 8, | |
| 9, | |
| 10, | |
| 13, | |
| 14, | |
| 15, | |
| 16, | |
| 17, | |
| 18, | |
| 20, | |
| 24, | |
| 26, | |
| 27, | |
| 28, | |
| 29, | |
| 30 | |
| ], | |
| "4": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11, | |
| 16, | |
| 19, | |
| 20, | |
| 22, | |
| 23, | |
| 25, | |
| 26, | |
| 27, | |
| 28, | |
| 29, | |
| 31 | |
| ], | |
| "5": [ | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11, | |
| 12, | |
| 13, | |
| 16, | |
| 19, | |
| 20, | |
| 21, | |
| 22, | |
| 23, | |
| 25, | |
| 26, | |
| 27, | |
| 28, | |
| 29, | |
| 30 | |
| ], | |
| "6": [ | |
| 0, | |
| 1, | |
| 6, | |
| 8, | |
| 11, | |
| 12, | |
| 13, | |
| 14, | |
| 17, | |
| 18, | |
| 19, | |
| 21, | |
| 22, | |
| 23, | |
| 25, | |
| 26, | |
| 29, | |
| 30 | |
| ], | |
| "7": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 11, | |
| 12, | |
| 13, | |
| 14, | |
| 16, | |
| 17, | |
| 18, | |
| 19, | |
| 20, | |
| 22, | |
| 23, | |
| 25, | |
| 26, | |
| 27, | |
| 29, | |
| 30, | |
| 31 | |
| ], | |
| "8": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 11, | |
| 12, | |
| 13, | |
| 14, | |
| 15, | |
| 16, | |
| 17, | |
| 18, | |
| 19, | |
| 21, | |
| 22, | |
| 25, | |
| 26, | |
| 27, | |
| 28, | |
| 29, | |
| 31 | |
| ], | |
| "9": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 6, | |
| 7, | |
| 9, | |
| 10, | |
| 11, | |
| 12, | |
| 14, | |
| 15, | |
| 17, | |
| 18, | |
| 20, | |
| 21, | |
| 22, | |
| 23, | |
| 24, | |
| 25, | |
| 27, | |
| 28, | |
| 29, | |
| 30, | |
| 31 | |
| ], | |
| "10": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 6, | |
| 7, | |
| 9, | |
| 11, | |
| 12, | |
| 13, | |
| 14, | |
| 15, | |
| 16, | |
| 17, | |
| 18, | |
| 20, | |
| 21, | |
| 22, | |
| 23, | |
| 24, | |
| 25, | |
| 26, | |
| 27, | |
| 29, | |
| 30, | |
| 31 | |
| ], | |
| "11": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 10, | |
| 12, | |
| 13, | |
| 14, | |
| 15, | |
| 16, | |
| 17, | |
| 18, | |
| 19, | |
| 22, | |
| 23, | |
| 24, | |
| 26, | |
| 27, | |
| 28, | |
| 29, | |
| 31 | |
| ], | |
| "12": [ | |
| 0, | |
| 2, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11, | |
| 12, | |
| 13, | |
| 14, | |
| 15, | |
| 16, | |
| 18, | |
| 19, | |
| 20, | |
| 22, | |
| 23, | |
| 24, | |
| 26, | |
| 27, | |
| 28, | |
| 29, | |
| 30, | |
| 31 | |
| ], | |
| "13": [ | |
| 0, | |
| 2, | |
| 3, | |
| 4, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11, | |
| 12, | |
| 13, | |
| 14, | |
| 15, | |
| 17, | |
| 18, | |
| 19, | |
| 20, | |
| 22, | |
| 23, | |
| 25, | |
| 26, | |
| 27, | |
| 28, | |
| 29, | |
| 30, | |
| 31 | |
| ], | |
| "14": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 7, | |
| 8, | |
| 10, | |
| 12, | |
| 13, | |
| 14, | |
| 15, | |
| 17, | |
| 18, | |
| 19, | |
| 20, | |
| 21, | |
| 22, | |
| 24, | |
| 25, | |
| 26, | |
| 27, | |
| 28, | |
| 30, | |
| 31 | |
| ], | |
| "15": [ | |
| 1, | |
| 2, | |
| 3, | |
| 5, | |
| 6, | |
| 7, | |
| 10, | |
| 11, | |
| 12, | |
| 14, | |
| 15, | |
| 16, | |
| 17, | |
| 19, | |
| 20, | |
| 23, | |
| 24, | |
| 25, | |
| 29, | |
| 30 | |
| ], | |
| "16": [ | |
| 0, | |
| 1, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 12, | |
| 13, | |
| 14, | |
| 15, | |
| 16, | |
| 17, | |
| 18, | |
| 19, | |
| 20, | |
| 22, | |
| 23, | |
| 25, | |
| 26, | |
| 28, | |
| 29, | |
| 30 | |
| ], | |
| "17": [ | |
| 0, | |
| 1, | |
| 2, | |
| 6, | |
| 8, | |
| 9, | |
| 12, | |
| 13, | |
| 14, | |
| 15, | |
| 16, | |
| 18, | |
| 19, | |
| 20, | |
| 22, | |
| 23, | |
| 25, | |
| 27, | |
| 29, | |
| 31 | |
| ], | |
| "18": [ | |
| 0, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 10, | |
| 11, | |
| 12, | |
| 13, | |
| 16, | |
| 18, | |
| 20, | |
| 21, | |
| 22, | |
| 23, | |
| 25, | |
| 26, | |
| 27, | |
| 28, | |
| 29, | |
| 31 | |
| ], | |
| "19": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 8, | |
| 10, | |
| 11, | |
| 12, | |
| 14, | |
| 15, | |
| 17, | |
| 18, | |
| 19, | |
| 20, | |
| 21, | |
| 24, | |
| 25, | |
| 26, | |
| 27, | |
| 28, | |
| 29, | |
| 30, | |
| 31 | |
| ], | |
| "20": [ | |
| 3, | |
| 6, | |
| 8, | |
| 9, | |
| 12, | |
| 17, | |
| 18, | |
| 22, | |
| 23, | |
| 25, | |
| 27, | |
| 28, | |
| 29, | |
| 30, | |
| 31 | |
| ], | |
| "21": [ | |
| 0, | |
| 1, | |
| 2, | |
| 6, | |
| 7, | |
| 8, | |
| 10, | |
| 12, | |
| 13, | |
| 14, | |
| 15, | |
| 16, | |
| 17, | |
| 18, | |
| 19, | |
| 20, | |
| 21, | |
| 22, | |
| 25, | |
| 27, | |
| 28, | |
| 29 | |
| ], | |
| "22": [ | |
| 0, | |
| 1, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 8, | |
| 9, | |
| 10, | |
| 12, | |
| 14, | |
| 15, | |
| 16, | |
| 17, | |
| 18, | |
| 19, | |
| 21, | |
| 22, | |
| 26, | |
| 28, | |
| 29, | |
| 30, | |
| 31 | |
| ], | |
| "23": [ | |
| 0, | |
| 1, | |
| 5, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11, | |
| 14, | |
| 15, | |
| 16, | |
| 17, | |
| 20, | |
| 25, | |
| 26, | |
| 27, | |
| 28, | |
| 30 | |
| ] | |
| }, | |
| "kept_experts_per_layer": { | |
| "0": [ | |
| 1, | |
| 2, | |
| 3, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11, | |
| 13, | |
| 16, | |
| 17, | |
| 22, | |
| 23, | |
| 24, | |
| 25, | |
| 26, | |
| 27, | |
| 28 | |
| ], | |
| "1": [ | |
| 0, | |
| 1, | |
| 2, | |
| 6, | |
| 10, | |
| 11, | |
| 12, | |
| 13, | |
| 15, | |
| 16, | |
| 17, | |
| 18, | |
| 20, | |
| 22, | |
| 26, | |
| 27, | |
| 28, | |
| 29, | |
| 30 | |
| ], | |
| "2": [ | |
| 0, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 8, | |
| 10, | |
| 20, | |
| 21, | |
| 22, | |
| 23, | |
| 24, | |
| 25, | |
| 27, | |
| 28, | |
| 29, | |
| 31 | |
| ], | |
| "3": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 7, | |
| 11, | |
| 12, | |
| 19, | |
| 21, | |
| 22, | |
| 23, | |
| 25, | |
| 31 | |
| ], | |
| "4": [ | |
| 6, | |
| 12, | |
| 13, | |
| 14, | |
| 15, | |
| 17, | |
| 18, | |
| 21, | |
| 24, | |
| 30 | |
| ], | |
| "5": [ | |
| 0, | |
| 6, | |
| 14, | |
| 15, | |
| 17, | |
| 18, | |
| 24, | |
| 31 | |
| ], | |
| "6": [ | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 7, | |
| 9, | |
| 10, | |
| 15, | |
| 16, | |
| 20, | |
| 24, | |
| 27, | |
| 28, | |
| 31 | |
| ], | |
| "7": [ | |
| 5, | |
| 10, | |
| 15, | |
| 21, | |
| 24, | |
| 28 | |
| ], | |
| "8": [ | |
| 9, | |
| 10, | |
| 20, | |
| 23, | |
| 24, | |
| 30 | |
| ], | |
| "9": [ | |
| 5, | |
| 8, | |
| 13, | |
| 16, | |
| 19, | |
| 26 | |
| ], | |
| "10": [ | |
| 5, | |
| 8, | |
| 10, | |
| 19, | |
| 28 | |
| ], | |
| "11": [ | |
| 9, | |
| 11, | |
| 20, | |
| 21, | |
| 25, | |
| 30 | |
| ], | |
| "12": [ | |
| 1, | |
| 3, | |
| 17, | |
| 21, | |
| 25 | |
| ], | |
| "13": [ | |
| 1, | |
| 5, | |
| 16, | |
| 21, | |
| 24 | |
| ], | |
| "14": [ | |
| 6, | |
| 9, | |
| 11, | |
| 16, | |
| 23, | |
| 29 | |
| ], | |
| "15": [ | |
| 0, | |
| 4, | |
| 8, | |
| 9, | |
| 13, | |
| 18, | |
| 21, | |
| 22, | |
| 26, | |
| 27, | |
| 28, | |
| 31 | |
| ], | |
| "16": [ | |
| 2, | |
| 11, | |
| 21, | |
| 24, | |
| 27, | |
| 31 | |
| ], | |
| "17": [ | |
| 3, | |
| 4, | |
| 5, | |
| 7, | |
| 10, | |
| 11, | |
| 17, | |
| 21, | |
| 24, | |
| 26, | |
| 28, | |
| 30 | |
| ], | |
| "18": [ | |
| 1, | |
| 9, | |
| 14, | |
| 15, | |
| 17, | |
| 19, | |
| 24, | |
| 30 | |
| ], | |
| "19": [ | |
| 6, | |
| 7, | |
| 9, | |
| 13, | |
| 16, | |
| 22, | |
| 23 | |
| ], | |
| "20": [ | |
| 0, | |
| 1, | |
| 2, | |
| 4, | |
| 5, | |
| 7, | |
| 10, | |
| 11, | |
| 13, | |
| 14, | |
| 15, | |
| 16, | |
| 19, | |
| 20, | |
| 21, | |
| 24, | |
| 26 | |
| ], | |
| "21": [ | |
| 3, | |
| 4, | |
| 5, | |
| 9, | |
| 11, | |
| 23, | |
| 24, | |
| 26, | |
| 30, | |
| 31 | |
| ], | |
| "22": [ | |
| 2, | |
| 7, | |
| 11, | |
| 13, | |
| 20, | |
| 23, | |
| 24, | |
| 25, | |
| 27 | |
| ], | |
| "23": [ | |
| 2, | |
| 3, | |
| 4, | |
| 6, | |
| 12, | |
| 13, | |
| 18, | |
| 19, | |
| 21, | |
| 22, | |
| 23, | |
| 24, | |
| 29, | |
| 31 | |
| ] | |
| }, | |
| "new_num_experts_per_layer": [ | |
| 19, | |
| 19, | |
| 17, | |
| 13, | |
| 10, | |
| 8, | |
| 14, | |
| 6, | |
| 6, | |
| 6, | |
| 5, | |
| 6, | |
| 5, | |
| 5, | |
| 6, | |
| 12, | |
| 6, | |
| 12, | |
| 8, | |
| 7, | |
| 17, | |
| 10, | |
| 9, | |
| 14 | |
| ] | |
| } | |