81 lines
2.1 KiB
Markdown
81 lines
2.1 KiB
Markdown
|
|
---
|
||
|
|
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
|
||
|
|
|
||
|
|
```
|