CultriX/MergeStage1

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using jpacifico/Chocolatine-2-14B-Instruct-v2.0.3 as a base.

Models Merged

The following models were included in the merge:

• jpacifico/Chocolatine-2-14B-Instruct-v2.0b3
• huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2
• sometimesanotion/Qwenvergence-14B-v12-Prose-DS
• allura-org/TQ2.5-14B-Sugarquill-v1
• underwoods/medius-erebus-magnum-14b
• arcee-ai/Virtuoso-Small-v2
• EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
• oxyapi/oxy-1-small

Configuration

The following YAML configuration was used to produce this model:

name: SuperMergedModel-v1
merge_method: model_stock
base_model: jpacifico/Chocolatine-2-14B-Instruct-v2.0.3  # Qwen-based
tokenizer_source: base  # Verify and update if needed
dtype: bfloat16
parameters:
  normalize: true
  rescale: false
  int8_mask: true
models:
  - model: arcee-ai/Virtuoso-Small-v2  # Qwen-based, IFEval focus
  - model: jpacifico/Chocolatine-2-14B-Instruct-v2.0b3  # Qwen-based, related to base
  - model: sometimesanotion/Qwenvergence-14B-v12-Prose-DS  # Qwen-based, good overall score
  - model: EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2  # Qwen-based, from Qwenvergence
  - model: oxyapi/oxy-1-small  # Qwen-based, from Qwenvergence
  - model: allura-org/TQ2.5-14B-Sugarquill-v1  # Qwen-based, from Qwenvergence
  - model: underwoods/medius-erebus-magnum-14b  # Qwen-based, from Qwenvergence
  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2  # Qwen-based, from Qwenvergence