| merge_method: dare_linear | |
| models: | |
| - model: MrRobotoAI/A5 | |
| parameters: | |
| weight: | |
| - filter: v_proj | |
| value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8] | |
| - filter: o_proj | |
| value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8] | |
| - filter: up_proj | |
| value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8] | |
| - filter: gate_proj | |
| value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8] | |
| - filter: down_proj | |
| value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8] | |
| - value: 1 | |
| - model: MrRobotoAI/A4 | |
| parameters: | |
| weight: | |
| - filter: v_proj | |
| value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2] | |
| - filter: o_proj | |
| value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2] | |
| - filter: up_proj | |
| value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2] | |
| - filter: gate_proj | |
| value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2] | |
| - filter: down_proj | |
| value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2] | |
| - value: 0 | |
| base_model: MrRobotoAI/A5 | |
| tokenizer_source: base | |
| dtype: bfloat16 |