spacematt/Qwen2.5-Vibe-Coder-14B-Instruct

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 Qwen/Qwen2.5-Coder-14B-Instruct as a base.

Models Merged

The following models were included in the merge:

• arcee-ai/Virtuoso-Small-v2
• spacematt/Qwen2.5-Composite-14B-Instruct
• sometimesanotion/Lamarck-14B-v0.7
• YOYO-AI/Qwen2.5-14B-YOYO-V5
• spacematt/Qwen2.5-Composite-Coder-14B-Instruct
• CultriX/Qwen2.5-14B-Ultimav2
• deepseek-ai/DeepSeek-R1-Distill-Qwen-14B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: CultriX/Qwen2.5-14B-Ultimav2
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
  - model: spacematt/Qwen2.5-Composite-14B-Instruct
  - model: arcee-ai/Virtuoso-Small-v2
  - model: spacematt/Qwen2.5-Composite-Coder-14B-Instruct
  - model: sometimesanotion/Lamarck-14B-v0.7
  - model: Qwen/Qwen2.5-Coder-14B-Instruct
  - model: YOYO-AI/Qwen2.5-14B-YOYO-V5
merge_method: model_stock
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
tokenizer_source: base
normalize: true
int8_mask: true
dtype: bfloat16