LeroyDyer's picture
Update README.md
7af1345 verified
---
base_model:
- LeroyDyer/Mixtral_AI_Cyber_3.m1
- LeroyDyer/Mixtral_AI_Cyber_3.1_SFT
- LeroyDyer/Mixtral_AI_Cyber_2.0
- LeroyDyer/Mixtral_AI_Cyber_1.0
- LeroyDyer/Mixtral_AI_Cyber_3.m2
- LeroyDyer/Mixtral_AI_Cyber_3.0
library_name: transformers
tags:
- biology
- chemistry
- medical
license: mit
language:
- en
metrics:
- bertscore
- code_eval
- character
---
### Models Merged
The following models were included in the merge:
* [LeroyDyer/Mixtral_AI_Cyber_3.m1](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_3.m1)
* [LeroyDyer/Mixtral_AI_Cyber_3.1_SFT](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_3.1_SFT)
* [LeroyDyer/Mixtral_AI_Cyber_2.0](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_2.0)
* [LeroyDyer/Mixtral_AI_Cyber_1.0](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_1.0)
* [LeroyDyer/Mixtral_AI_Cyber_3.0](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_3.0)
A Merges of my best models !:
A very great model as it contains the deltas from all of the very hard trained models : all these models were heavy coders!
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: LeroyDyer/Mixtral_AI_Cyber_3.m2
parameters:
density: [0.256, 0.512, 0.128] # density gradient
weight: 0.382
- model: LeroyDyer/Mixtral_AI_Cyber_2.0
parameters:
density: 0.382
weight: [0.256, 0.128, 0.256, 0.128] # weight gradient
- model: LeroyDyer/Mixtral_AI_Cyber_3.0
parameters:
density: 0.382
weight: [0.128, 0.512, 0.128, 0.128] # weight gradient
- model: LeroyDyer/Mixtral_AI_Cyber_3.m1
parameters:
density: 0.382
weight: [0.256, 0.256, 0.512, 0.128] # weight gradient
- model: LeroyDyer/Mixtral_AI_Cyber_1.0
parameters:
density: 0.382
weight: [0.128, 0.512, 0.128, 0.128] # weight gradient
- model: LeroyDyer/Mixtral_AI_Cyber_3.1_SFT
parameters:
density: 0.382
weight:
- filter: mlp
value: 0.5
- value: 0
merge_method: ties
base_model: LeroyDyer/Mixtral_AI_Cyber_3.m2
parameters:
normalize: true
int8_mask: true
dtype: float16
```