| out_dtype: bfloat16 | |
| dtype: float32 | |
| tokenizer_source: base | |
| merge_method: della_linear | |
| parameters: | |
| int8_mask: true | |
| density: 0.5 | |
| epsilon: 0.04 | |
| lambda: 1.05 | |
| base_model: nbeerbower/Llama3.1-Allades-8B | |
| models: | |
| - model: nbeerbower/Llama3.1-Allades-8B | |
| parameters: | |
| weight: | |
| - filter: v_proj | |
| value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1] | |
| - filter: o_proj | |
| value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1] | |
| - filter: up_proj | |
| value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1] | |
| - filter: gate_proj | |
| value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1] | |
| - filter: down_proj | |
| value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1] | |
| - value: 1 | |
| - model: mergekit-community/L3.1-Pneuma-8B-v1 | |
| parameters: | |
| weight: | |
| - filter: v_proj | |
| value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0] | |
| - filter: o_proj | |
| value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0] | |
| - filter: up_proj | |
| value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0] | |
| - filter: gate_proj | |
| value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0] | |
| - filter: down_proj | |
| value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0] | |
| - value: 0 | |