README.md

metadata

base_model:
  - qingy2024/UwU-7B-Instruct
  - prithivMLmods/QwQ-LCoT-7B-Instruct
  - bunnycore/FuseQwQen-7B
  - bunnycore/QandoraExp-7B-Persona
library_name: transformers
tags:
  - mergekit
  - merge

FwF-Qwen-7B-0.1 is a large language model that is created by merging three other models: UwU-7B-Instruct, QwQ-LCoT-7B-Instruct, and QandoraExp-7B-Persona. These models are specialized for reasoning, long thinking, roleplay, and general tasks, respectively.

Merge Method

This model was merged using the TIES merge method using bunnycore/FuseQwQen-7B as a base.

Models Merged

The following models were included in the merge:

• qingy2024/UwU-7B-Instruct
• prithivMLmods/QwQ-LCoT-7B-Instruct
• bunnycore/QandoraExp-7B-Persona

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: bunnycore/FuseQwQen-7B
    parameters:
      weight: 0.5
  - model: prithivMLmods/QwQ-LCoT-7B-Instruct
    parameters:
      weight: 0.5
  - model: bunnycore/QandoraExp-7B-Persona
    parameters:
      weight: 0.5
  - model: qingy2024/UwU-7B-Instruct
    parameters:
      weight: 0.5
base_model: bunnycore/FuseQwQen-7B
merge_method: ties