|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: |
|
|
- anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
--- |
|
|
An upscale of anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
|
|
|
```yaml |
|
|
slices: |
|
|
- sources: |
|
|
- layer_range: [0, 4] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
- sources: |
|
|
- layer_range: [2, 4] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0 |
|
|
- filter: down_proj |
|
|
value: 0 |
|
|
- value: 1 |
|
|
- sources: |
|
|
- layer_range: [4, 8] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
- sources: |
|
|
- layer_range: [6, 8] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0 |
|
|
- filter: down_proj |
|
|
value: 0 |
|
|
- value: 1 |
|
|
- sources: |
|
|
- layer_range: [8, 12] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
- sources: |
|
|
- layer_range: [10, 12] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0 |
|
|
- filter: down_proj |
|
|
value: 0 |
|
|
- value: 1 |
|
|
- sources: |
|
|
- layer_range: [12, 16] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
- sources: |
|
|
- layer_range: [14, 16] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0 |
|
|
- filter: down_proj |
|
|
value: 0 |
|
|
- value: 1 |
|
|
- sources: |
|
|
- layer_range: [16, 20] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
- sources: |
|
|
- layer_range: [18, 20] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0 |
|
|
- filter: down_proj |
|
|
value: 0 |
|
|
- value: 1 |
|
|
- sources: |
|
|
- layer_range: [20, 24] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
- sources: |
|
|
- layer_range: [22, 24] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0 |
|
|
- filter: down_proj |
|
|
value: 0 |
|
|
- value: 1 |
|
|
- sources: |
|
|
- layer_range: [24, 28] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
- sources: |
|
|
- layer_range: [26, 28] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0 |
|
|
- filter: down_proj |
|
|
value: 0 |
|
|
- value: 1 |
|
|
- sources: |
|
|
- layer_range: [28, 32] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
- sources: |
|
|
- layer_range: [30, 32] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0 |
|
|
- filter: down_proj |
|
|
value: 0 |
|
|
- value: 1 |
|
|
- sources: |
|
|
- layer_range: [32, 36] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
- sources: |
|
|
- layer_range: [34, 36] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0 |
|
|
- filter: down_proj |
|
|
value: 0 |
|
|
- value: 1 |
|
|
- sources: |
|
|
- layer_range: [36, 40] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
- sources: |
|
|
- layer_range: [38, 40] |
|
|
model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0 |
|
|
- filter: down_proj |
|
|
value: 0 |
|
|
- value: 1 |
|
|
merge_method: passthrough |
|
|
dtype: bfloat16 |
|
|
``` |
