|
--- |
|
base_model: |
|
- win10/Phi-3.5-mini-instruct-24-9-29 |
|
- FreedomIntelligence/Apollo2-3.8B |
|
- ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1 |
|
- AXCXEPT/Borea-Phi-3.5-mini-Instruct-Common |
|
- microsoft/Phi-3.5-mini-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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [win10/Phi-3.5-mini-instruct-24-9-29](https://huggingface.co/win10/Phi-3.5-mini-instruct-24-9-29) |
|
* [FreedomIntelligence/Apollo2-3.8B](https://huggingface.co/FreedomIntelligence/Apollo2-3.8B) |
|
* [ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1](https://huggingface.co/ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1) |
|
* [AXCXEPT/Borea-Phi-3.5-mini-Instruct-Common](https://huggingface.co/AXCXEPT/Borea-Phi-3.5-mini-Instruct-Common) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: microsoft/Phi-3.5-mini-instruct |
|
#no parameters necessary for base model |
|
- model: FreedomIntelligence/Apollo2-3.8B |
|
parameters: |
|
density: 1 |
|
weight: 1 |
|
- model: ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1 |
|
parameters: |
|
density: 1 |
|
weight: 1 |
|
- model: AXCXEPT/Borea-Phi-3.5-mini-Instruct-Common |
|
parameters: |
|
density: 1 |
|
weight: 1 |
|
- model: win10/Phi-3.5-mini-instruct-24-9-29 |
|
parameters: |
|
density: 1 |
|
weight: 1 |
|
merge_method: ties |
|
base_model: microsoft/Phi-3.5-mini-instruct |
|
parameters: |
|
normalize: false |
|
int8_mask: true |
|
dtype: float16 |
|
``` |
|
|
