README.md

metadata

base_model:
  - Qwen/Qwen2.5-14B-Instruct
  - Qwen/Qwen2.5-14B
  - CultriX/Qwen2.5-14B_Virtuoso-small-v2-LoRA_r128
library_name: transformers
tags:
  - mergekit
  - merge

MergeStage3v1

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using Qwen/Qwen2.5-14B as a base.

Models Merged

The following models were included in the merge:

• Qwen/Qwen2.5-14B-Instruct
• CultriX/Qwen2.5-14B_Virtuoso-small-v2-LoRA_r128

Configuration

The following YAML configuration was used to produce this model:

name: Virtuoso-Infused-Qwen
merge_method: dare_ties
base_model: Qwen/Qwen2.5-14B # New Base Model
tokenizer_source: base
dtype: float32
out_dtype: bfloat16
models:
  - model: Qwen/Qwen2.5-14B-Instruct
    parameters:
      weight: 1.0
      density: 1.0
  - model: CultriX/Qwen2.5-14B_Virtuoso-small-v2-LoRA_r128
    parameters:
      weight: 1.0
      density: 1.0