qwen2.5-7b-upscaled / README.md
ehristoforu's picture
Upload folder using huggingface_hub
3da7a68 verified
---
base_model:
- Qwen/Qwen2.5-7B-Instruct
library_name: transformers
tags:
- mergekit
- merge
---
# merge
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/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
merge_method: passthrough
slices:
- sources:
- layer_range: [0, 19]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [19, 20]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [19, 20]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [19, 20]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [20, 21]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [20, 21]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [20, 21]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [21, 22]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [21, 22]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [21, 22]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [22, 23]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [22, 23]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [22, 23]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [23, 24]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [23, 24]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [23, 24]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [24, 25]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [24, 25]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [24, 25]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [25, 26]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [25, 26]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [25, 26]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [26, 27]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [26, 27]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [26, 27]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [27, 28]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [27, 28]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [27, 28]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
```