metadata

base_model:
  - LeroyDyer/_Spydaz_Web_AI_AGI_R1_Math_AdvancedStudent
  - LeroyDyer/_Spydaz_Web_AI_AGI_R1_Top_Student
  - TIGER-Lab/MAmmoTH2-7B-Plus
  - LeroyDyer/_Spydaz_Web_AI_AGI_R1_Math_003
library_name: transformers
tags:
  - mergekit
  - merge

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using LeroyDyer/_Spydaz_Web_AI_AGI_R1_Top_Student as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


models:
  - model: TIGER-Lab/MAmmoTH2-7B-Plus
    parameters:
      density: 0.386
      weight: [0.386, 0.128, 0.768, 0.256] # weight gradient
  - model: LeroyDyer/_Spydaz_Web_AI_AGI_R1_Math_003
    parameters:
      density: 0.256
      weight: [0.256, 0.386, 0.256, 0.768] # weight gradient
  - model: LeroyDyer/_Spydaz_Web_AI_AGI_R1_Top_Student
    parameters:
      density: 0.512
      weight: [0.256, 0.512, 0.768, 0.512] # weight gradient
  - model: LeroyDyer/_Spydaz_Web_AI_AGI_R1_Math_AdvancedStudent
    parameters:
      density: 0.768
      weight:
        - filter: mlp
          value: 0.768
        - value: 0.128
merge_method: ties
base_model: LeroyDyer/_Spydaz_Web_AI_AGI_R1_Top_Student
parameters:
  normalize: true
  int8_mask: true
dtype: float16