|
models: |
|
- model: tokyotech-llm/Swallow-13b-instruct-hf |
|
|
|
- model: allenai/tulu-2-dpo-13b |
|
parameters: |
|
density: 1 |
|
weight: |
|
- filter: mlp.down_proj |
|
value: [0.45, 0.10, 0.45, 0.10, 0.45, 0.10, 0.45, 0.10, 0.10] |
|
- filter: mlp.gate_proj |
|
value: [0.70, 0.10, 0.45, 0.10, 0.45, 0.10, 0.45, 0.10, 0.10] |
|
- filter: mlp.up_proj |
|
value: [0.70, 0.10, 0.45, 0.10, 0.45, 0.10, 0.45, 0.10, 0.10] |
|
- filter: self_attn |
|
value: [0.70, 0.45, 0.10, 0.45, 0.10, 0.45, 0.10, 0.45, 0.45] |
|
- value: 0 |
|
merge_method: dare_ties |
|
base_model: tokyotech-llm/Swallow-13b-instruct-hf |
|
dtype: bfloat16 |
|
tokenizer_source: union |
|
name: Superswallow-13b-v0.2-flavor |
|
--- |
|
slices: |
|
- sources: |
|
- model: nitky/Superswallow-13b-baseline |
|
layer_range: [0, 40] |
|
- model: Superswallow-13b-v0.2-flavor |
|
layer_range: [0, 40] |
|
merge_method: slerp |
|
base_model: nitky/Superswallow-13b-baseline |
|
parameters: |
|
t: |
|
- filter: self_attn |
|
value: [0, 0.5, 0.3, 0.7, 1] |
|
- filter: mlp |
|
value: [1, 0.5, 0.7, 0.3, 0] |
|
- value: 0.5 |
|
dtype: bfloat16 |
|
name: Superswallow-13b-v0.2 |
|
|