s1ghhh/which16_merged

best

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

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• neuralmagic/Llama-2-7b-evolcodealpaca
• meta-math/MetaMath-7B-V1.0
• lmsys/vicuna-7b-v1.5
• teknium/OpenHermes-7B
• migtissera/Synthia-7B-v1.2
• meta-llama/Llama-2-7b-chat-hf

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: migtissera/Synthia-7B-v1.2
    parameters:
      weight: 0.25088
  - model: neuralmagic/Llama-2-7b-evolcodealpaca
    parameters:
      weight: 0.06272
  - model: teknium/OpenHermes-7B
    parameters:
      weight: 0.0784
  - model: meta-llama/Llama-2-7b-chat-hf
    parameters:
      weight: 0.098
  - model: meta-math/MetaMath-7B-V1.0
    parameters:
      weight: 0.21
  - model: lmsys/vicuna-7b-v1.5
    parameters:
      weight: 0.3
merge_method: linear
dtype: bfloat16