Qwen2.5 CompositeFlow Coder 14B Instruct

🚀 Merged Language Model

This project creates a merged pre - trained language model using the mergekit tool, which combines multiple Qwen2.5 - based models to potentially enhance performance and functionality.

🚀 Quick Start

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

✨ Features

• Utilizes the Model Stock merge method.
• Based on Qwen/Qwen2.5-Coder-14B-Instruct.
• Merges multiple Qwen2.5 - related models for potentially better performance.

📚 Documentation

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:

• spacematt/Qwen2.5-Composite-14B-Instruct
• spacematt/Qwen2.5-Flow-Coder-14B-Instruct
• spacematt/Qwen2.5-Composite-Coder-14B-Instruct
• spacematt/Qwen2.5-Vibe-Coder-14B-Instruct
• spacematt/Qwen2.5-Sharp-Coder-14B-Instruct

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: spacematt/Qwen2.5-Composite-14B-Instruct
  - model: spacematt/Qwen2.5-Composite-Coder-14B-Instruct
  - model: spacematt/Qwen2.5-Vibe-Coder-14B-Instruct
  - model: spacematt/Qwen2.5-Sharp-Coder-14B-Instruct
  - model: spacematt/Qwen2.5-Flow-Coder-14B-Instruct
merge_method: model_stock
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
tokenizer_source: base
normalize: true
int8_mask: true
dtype: bfloat16

📄 License

This project is licensed under the apache-2.0 license.