|
|
---
|
|
|
base_model:
|
|
|
- TroyDoesAI/Llama-3.2-4B
|
|
|
- TroyDoesAI/BlackSheep-RAG-4B
|
|
|
library_name: transformers
|
|
|
tags:
|
|
|
- mergekit
|
|
|
- merge
|
|
|
|
|
|
---
|
|
|
# BlackSheep
|
|
|
|
|
|
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 SLERP merge method.
|
|
|
|
|
|
### Models Merged
|
|
|
|
|
|
The following models were included in the merge:
|
|
|
* [TroyDoesAI/Llama-3.2-4B](https://huggingface.co/TroyDoesAI/Llama-3.2-4B)
|
|
|
* [TroyDoesAI/BlackSheep-RAG-4B](https://huggingface.co/TroyDoesAI/BlackSheep-RAG-4B)
|
|
|
|
|
|
### Configuration
|
|
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
|
|
```yaml
|
|
|
slices:
|
|
|
- sources:
|
|
|
- model: TroyDoesAI/BlackSheep-RAG-4B
|
|
|
layer_range: [0, 42]
|
|
|
- model: TroyDoesAI/Llama-3.2-4B
|
|
|
layer_range: [0, 42]
|
|
|
|
|
|
merge_method: slerp
|
|
|
base_model: TroyDoesAI/Llama-3.2-4B
|
|
|
parameters:
|
|
|
t:
|
|
|
- filter: self_attn
|
|
|
value: [0, 0.5, 0.3, 0.7, 1]
|
|
|
- filter: mlp
|
|
|
value: [1, 0.5, 0.7, 0.3, 0]
|
|
|
- value: 0.50 # fallback for rest of tensors
|
|
|
dtype: bfloat16
|
|
|
|
|
|
```
|
|
|
|
