spacematt/Qwen2.5-Casual-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 spacematt/Qwen2.5-CompositeFlow-Coder-14B-Instruct as a base.

Models Merged

The following models were included in the merge:

• CultriX/Qwen2.5-14B-Wernicke
• deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
• tanliboy/lambda-qwen2.5-14b-dpo-test
• djuna/Q2.5-Veltha-14B-0.5
• Triangle104/Herodotos-14B
• suayptalha/Lamarckvergence-14B
• wanlige/li-14b-v0.4
• sometimesanotion/Lamarck-14B-v0.7
• YOYO-AI/Qwen2.5-14B-YOYO-V5
• deepcogito/cogito-v1-preview-qwen-14B
• arcee-ai/Virtuoso-Small-v2
• CultriX/Qwen2.5-14B-Ultimav2

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
  - model: CultriX/Qwen2.5-14B-Wernicke
  - model: CultriX/Qwen2.5-14B-Ultimav2
  - model: wanlige/li-14b-v0.4
  - model: tanliboy/lambda-qwen2.5-14b-dpo-test
  - model: arcee-ai/Virtuoso-Small-v2
  - model: sometimesanotion/Lamarck-14B-v0.7
  - model: suayptalha/Lamarckvergence-14B
  - model: YOYO-AI/Qwen2.5-14B-YOYO-V5
  - model: deepcogito/cogito-v1-preview-qwen-14B
  - model: Triangle104/Herodotos-14B
  - model: djuna/Q2.5-Veltha-14B-0.5
merge_method: model_stock
base_model: spacematt/Qwen2.5-CompositeFlow-Coder-14B-Instruct
normalize: true
int8_mask: true
dtype: bfloat16