| # 32 layers -> VS 40 | |
| #models: | |
| # - model: G:/7B/L3-8B-Stheno-v3.2 | |
| # - model: G:/7B/Llama-3-Lumimaid-8B-v0.1-OAS | |
| # - model: G:/7B/L3-Jamet-8B-MK.V-Blackroot | |
| #merge_method: model_stock | |
| #base_model: G:/7B/L3-8B-Stheno-v3.2 | |
| #dtype: float32 | |
| slices: | |
| - sources: | |
| - model: G:/7B/L3-8B-Stheno-v3.2 | |
| layer_range: [0, 14] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 1 | |
| - filter: down_proj | |
| value: 1 | |
| - value: 1 | |
| - sources: | |
| - model: G:/7B/L3-Lumimaid-8B-v0.1-OAS | |
| layer_range: [8, 20] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 1 | |
| - filter: down_proj | |
| value: 1 | |
| - value: 1 | |
| - sources: | |
| - model: G:/7B/L3-Jamet-8B-MK.V-Blackroot | |
| layer_range: [12, 24] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 1 | |
| - filter: down_proj | |
| value: 1 | |
| - value: 1 | |
| - sources: | |
| - model: G:/7B/L3-8B-Stheno-v3.2 | |
| layer_range: [14, 20] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: .8 | |
| - filter: down_proj | |
| value: .8 | |
| - value: .8 | |
| - sources: | |
| - model: G:/7B/L3-8B-Stheno-v3.2 | |
| layer_range: [20, 25] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: .8 | |
| - filter: down_proj | |
| value: .8 | |
| - value: .8 | |
| - sources: | |
| - model: G:/7B/L3-8B-Stheno-v3.2 | |
| layer_range: [25, 27] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: .6 | |
| - filter: down_proj | |
| value: .6 | |
| - value: 1 | |
| - sources: | |
| - model: G:/7B/L3-8B-Stheno-v3.2 | |
| layer_range: [27, 28] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: .9 | |
| - filter: down_proj | |
| value: .9 | |
| - value: 1 | |
| - sources: | |
| - model: G:/7B/L3-Lumimaid-8B-v0.1-OAS | |
| layer_range: [20, 25] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 1 | |
| - filter: down_proj | |
| value: 1 | |
| - value: 1 | |
| - sources: | |
| - model: G:/7B/L3-Lumimaid-8B-v0.1-OAS | |
| layer_range: [25, 27] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: .6 | |
| - filter: down_proj | |
| value: .6 | |
| - value: 1 | |
| - sources: | |
| - model: G:/7B/L3-Lumimaid-8B-v0.1-OAS | |
| layer_range: [27, 31] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 1 | |
| - filter: down_proj | |
| value: 1 | |
| - value: 1 | |
| - sources: | |
| - model: G:/7B/L3-Jamet-8B-MK.V-Blackroot | |
| layer_range: [24, 31] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 1 | |
| - filter: down_proj | |
| value: 1 | |
| - value: 1 | |
| - sources: | |
| - model: G:/7B/L3-Jamet-8B-MK.V-Blackroot | |
| layer_range: [31, 32] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 0.3333333333333 | |
| - filter: down_proj | |
| value: 0.3333333333333 | |
| - value: 0.3333333333333 | |
| - sources: | |
| - model: G:/7B/L3-Jamet-8B-MK.V-Blackroot | |
| layer_range: [31, 32] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 0.4444444444444 | |
| - filter: down_proj | |
| value: 0.4444444444444 | |
| - value: 0.4444444444444 | |
| - sources: | |
| - model: G:/7B/L3-Jamet-8B-MK.V-Blackroot | |
| layer_range: [31, 32] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 0.5555555555555 | |
| - filter: down_proj | |
| value: 0.5555555555555 | |
| - value: 0.5555555555555 | |
| - sources: | |
| - model: G:/7B/L3-Jamet-8B-MK.V-Blackroot | |
| layer_range: [31, 32] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 0.6666666666666 | |
| - filter: down_proj | |
| value: 0.6666666666666 | |
| - value: 0.6666666666666 | |
| - sources: | |
| - model: G:/7B/L3-Jamet-8B-MK.V-Blackroot | |
| layer_range: [31, 32] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 0.7777777777777 | |
| - filter: down_proj | |
| value: 0.7777777777777 | |
| - value: 0.8888888888888 | |
| merge_method: passthrough | |
| dtype: float16 |