|
|
|
slices: |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 0 |
|
- 4 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 3 |
|
- 4 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0 |
|
- filter: down_proj |
|
value: 0 |
|
- value: 1 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 4 |
|
- 8 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 7 |
|
- 8 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0 |
|
- filter: down_proj |
|
value: 0 |
|
- value: 1 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 8 |
|
- 12 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 11 |
|
- 12 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0 |
|
- filter: down_proj |
|
value: 0 |
|
- value: 1 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 12 |
|
- 16 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 15 |
|
- 16 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0 |
|
- filter: down_proj |
|
value: 0 |
|
- value: 1 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 16 |
|
- 20 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 19 |
|
- 20 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0 |
|
- filter: down_proj |
|
value: 0 |
|
- value: 1 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 20 |
|
- 24 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 23 |
|
- 24 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0 |
|
- filter: down_proj |
|
value: 0 |
|
- value: 1 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 24 |
|
- 28 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 27 |
|
- 28 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0 |
|
- filter: down_proj |
|
value: 0 |
|
- value: 1 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 28 |
|
- 32 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 31 |
|
- 32 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0 |
|
- filter: down_proj |
|
value: 0 |
|
- value: 1 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 32 |
|
- 36 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 35 |
|
- 36 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0 |
|
- filter: down_proj |
|
value: 0 |
|
- value: 1 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 36 |
|
- 40 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 39 |
|
- 40 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0 |
|
- filter: down_proj |
|
value: 0 |
|
- value: 1 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 40 |
|
- 44 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 43 |
|
- 44 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0 |
|
- filter: down_proj |
|
value: 0 |
|
- value: 1 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 44 |
|
- 48 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 47 |
|
- 48 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0 |
|
- filter: down_proj |
|
value: 0 |
|
- value: 1 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 48 |
|
- 52 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 51 |
|
- 52 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0 |
|
- filter: down_proj |
|
value: 0 |
|
- value: 1 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 52 |
|
- 56 |
|
- sources: |
|
- model: mistral-community/Codestral-22B-v0.1 |
|
layer_range: |
|
- 55 |
|
- 56 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0 |
|
- filter: down_proj |
|
value: 0 |
|
- value: 1 |
|
|
|
merge_method: passthrough |
|
dtype: bfloat16 |
|
|