|
models: |
|
- model: tokyotech-llm/Swallow-70b-instruct-hf |
|
|
|
- model: nitky/Swallow-70b-NVE-RP |
|
parameters: |
|
density: 1 |
|
weight: |
|
- filter: mlp |
|
value: 0.1 |
|
- filter: self_attn |
|
value: 0.4 |
|
- value: 0 |
|
merge_method: dare_ties |
|
base_model: tokyotech-llm/Swallow-70b-instruct-hf |
|
dtype: bfloat16 |
|
tokenizer_source: union |
|
name: Swallow-70b-RP-base |
|
--- |
|
models: |
|
- model: tokyotech-llm/Swallow-70b-instruct-hf |
|
|
|
- model: nitky/Swallow-70b-NVE-RP |
|
parameters: |
|
density: 1 |
|
weight: |
|
- filter: mlp |
|
value: [0.4, 0.1, 0.4, 0.1, 0.4, 0.1, 0.4, 0.1, 0.1] |
|
- filter: self_attn |
|
value: [0.4, 0.4, 0.1, 0.4, 0.1, 0.4, 0.1, 0.4, 0.4] |
|
- value: 0 |
|
merge_method: dare_ties |
|
base_model: tokyotech-llm/Swallow-70b-instruct-hf |
|
dtype: bfloat16 |
|
tokenizer_source: union |
|
name: Swallow-70b-RP-flavor |
|
--- |
|
slices: |
|
- sources: |
|
- model: Swallow-70b-RP-base |
|
layer_range: [0, 80] |
|
- model: Swallow-70b-RP-flavor |
|
layer_range: [0, 80] |
|
merge_method: slerp |
|
base_model: Swallow-70b-RP-base |
|
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: Swallow-70b-RP |
|
|