README.md

metadata

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
• LeroyDyer/Mixtral_AI_Cyber_3.1_SFT
• LeroyDyer/Mixtral_AI_Cyber_2.0
• LeroyDyer/Mixtral_AI_Cyber_1.0
• 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:

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