RichardErkhov/Marsouuu_-_MiniMathExpert-2_61B-ECE-PRYMMAL-Martial-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MiniMathExpert-2_61B-ECE-PRYMMAL-Martial - GGUF

• —Model creator: https://huggingface.co/Marsouuu/
• —Original model: https://huggingface.co/Marsouuu/MiniMathExpert-2_61B-ECE-PRYMMAL-Martial/

Original model description: --- base_model:

• —cognitivecomputations/dolphin-2.9.4-gemma2-2b
• —google/gemma-2-2b library_name: transformers tags:
• —mergekit
• —merge license: apache-2.0 ---

my-output

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• —cognitivecomputations/dolphin-2.9.4-gemma2-2b
• —google/gemma-2-2b

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources: 
      - model: cognitivecomputations/dolphin-2.9.4-gemma2-2b
        layer_range: [0, 26]
      - model: google/gemma-2-2b
        layer_range: [0, 26]    
merge_method: slerp
base_model: google/gemma-2-2b
parameters:
  t:
    - filter: self_attn
      value: [0, 0.25, 0.5, 0.75, 1]
    - filter: mlp
      value: [1, 0.75, 0.5, 0.25, 0]
    - value: 0.5
dtype: bfloat16