|
dtype: bfloat16 |
|
tokenizer_source: base |
|
merge_method: nuslerp |
|
parameters: |
|
nuslerp_row_wise: true |
|
models: |
|
- model: unsloth/Llama-3.3-70B-Instruct |
|
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: Step1 |
|
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 |