43 lines
917 B
Markdown
43 lines
917 B
Markdown
---
|
|
base_model:
|
|
- Nanbeige/Nanbeige4.1-3B
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
|
|
---
|
|
# Nanbeige-5B-Frankenmerge
|
|
|
|
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 using [Nanbeige/Nanbeige4.1-3B](https://huggingface.co/Nanbeige/Nanbeige4.1-3B) as a base.
|
|
|
|
### Models Merged
|
|
|
|
The following models were included in the merge:
|
|
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
slices:
|
|
- sources:
|
|
- model: Nanbeige/Nanbeige4.1-3B
|
|
layer_range: [0, 24]
|
|
- sources:
|
|
- model: Nanbeige/Nanbeige4.1-3B
|
|
layer_range: [12, 28]
|
|
- sources:
|
|
- model: Nanbeige/Nanbeige4.1-3B
|
|
layer_range: [16, 32]
|
|
merge_method: passthrough
|
|
base_model: Nanbeige/Nanbeige4.1-3B
|
|
dtype: float16
|
|
```
|