|
|
--- |
|
|
base_model: |
|
|
- Qwen/Qwen3-14B-Base |
|
|
library_name: transformers |
|
|
tags: |
|
|
- mergekit |
|
|
- merge |
|
|
|
|
|
--- |
|
|
# upscaled-zero |
|
|
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
|
|
## Merge Details |
|
|
### Merge Method |
|
|
|
|
|
This model was merged using the Passthrough merge method. |
|
|
|
|
|
### Models Merged |
|
|
|
|
|
The following models were included in the merge: |
|
|
* [Qwen/Qwen3-14B-Base](https://huggingface.co/Qwen/Qwen3-14B-Base) |
|
|
|
|
|
### Configuration |
|
|
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
|
|
```yaml |
|
|
slices: |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [0,25] |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [25,26] |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [25,26] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [25,26] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [26,27] |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [26,27] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [26,27] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [27,28] |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [27,28] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [27,28] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [28,29] |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [28,29] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [28,29] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [29,30] |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [29,30] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [29,30] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [30,31] |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [30,31] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [30,31] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [31,32] |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [31,32] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [31,32] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [32,33] |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [32,33] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [32,33] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [33,34] |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [33,34] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [33,34] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [34,35] |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [34,35] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [34,35] |
|
|
parameters: |
|
|
scale: |
|
|
- filter: o_proj |
|
|
value: 0.0 |
|
|
- filter: down_proj |
|
|
value: 0.0 |
|
|
- value: 1.0 |
|
|
- sources: |
|
|
- model: Qwen/Qwen3-14B-Base |
|
|
layer_range: [35,40] |
|
|
merge_method: passthrough |
|
|
``` |
|
|
|