|
--- |
|
base_model: |
|
- mistralai/Mistral-7B-Instruct-v0.2 |
|
- LeroyDyer/Mixtral_AI_Cyber_3.0 |
|
- LeroyDyer/Mixtral_AI_MultiToken |
|
- LeroyDyer/Mixtral_AI_Multi_TEST |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
- code |
|
- art |
|
- Cyber-Series |
|
datasets: |
|
- WhiteRabbitNeo/WRN-Chapter-1 |
|
- WhiteRabbitNeo/WRN-Chapter-2 |
|
- CyberNative/Code_Vulnerability_Security_DPO |
|
license: apache-2.0 |
|
--- |
|
UNDER DEVELOPMENT |
|
[<img src="https://cdn-avatars.huggingface.co/v1/production/uploads/65d883893a52cd9bcd8ab7cf/tRsCJlHNZo1D02kBTmfy9.jpeg" width="200"/> |
|
https://github.com/spydaz |
|
|
|
This model is being constantly retuned and updated ! (these updates may not be reflected in the current gguf!) |
|
|
|
This is a highly focused model which is dedicated to producing code and functions and applications. |
|
It has been erged with the top models of this repo and will be fine tuned on datasets dedicated to coding problems and other code related tasks. such as uml diagrams and object oriented planning etc. |
|
|
|
# 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 [LeroyDyer/Mixtral_AI_Cyber_3.0](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_3.0) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) |
|
* [LeroyDyer/Mixtral_AI_MultiToken](https://huggingface.co/LeroyDyer/Mixtral_AI_MultiToken) |
|
* [LeroyDyer/Mixtral_AI_Multi_TEST](https://huggingface.co/LeroyDyer/Mixtral_AI_Multi_TEST) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
|
|
models: |
|
- model: LeroyDyer/Mixtral_AI_Multi_TEST |
|
parameters: |
|
density: [0.87, 0.721, 0.451] # density gradient |
|
weight: 0.876 |
|
- model: LeroyDyer/Mixtral_AI_MultiToken |
|
parameters: |
|
density: 0.232 |
|
weight: [0.36, 0.3, 0.437, 0.76] # weight gradient |
|
- model: mistralai/Mistral-7B-Instruct-v0.2 |
|
parameters: |
|
density: 0.475 |
|
weight: |
|
- filter: mlp |
|
value: 0.5 |
|
- value: 0 |
|
merge_method: ties |
|
base_model: LeroyDyer/Mixtral_AI_Cyber_3.0 |
|
parameters: |
|
normalize: true |
|
int8_mask: true |
|
dtype: float16 |
|
|
|
``` |
