| dtype: bfloat16 | |
| tokenizer_source: base | |
| merge_method: della_linear | |
| parameters: | |
| density: 0.5 | |
| base_model: SchisandraVA3 | |
| models: | |
| - model: unsloth/Mistral-Small-Instruct-2409 | |
| parameters: | |
| weight: | |
| - filter: v_proj | |
| value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0] | |
| - filter: o_proj | |
| value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1] | |
| - filter: up_proj | |
| value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] | |
| - filter: gate_proj | |
| value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0] | |
| - filter: down_proj | |
| value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0] | |
| - value: 0 | |
| - model: SchisandraVA3 | |
| parameters: | |
| weight: | |
| - filter: v_proj | |
| value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1] | |
| - filter: o_proj | |
| value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0] | |
| - filter: up_proj | |
| value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0] | |
| - filter: gate_proj | |
| value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1] | |
| - filter: down_proj | |
| value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] | |
| - value: 1 |