đ Model Merge Project
This project focuses on merging pre - trained language models, offering a new integrated model with enhanced capabilities. It uses the mergekit tool to achieve the merging process.
đ Quick Start
This is a merge of pre - trained language models created using mergekit.
⨠Features
- Utilizes the Model Stock merge method.
- Merges multiple Qwen2.5 - based models to potentially enhance performance and functionality.
đ Documentation
Merge Details
Merge Method
This model was merged using the Model Stock merge method using [spacematt/Qwen2.5 - Channel - Coder - 14B - Instruct](https://huggingface.co/spacematt/Qwen2.5 - Channel - Coder - 14B - Instruct) as a base.
Models Merged
The following models were included in the merge:
- [spacematt/Qwen2.5 - Composite - Coder - 14B - Instruct](https://huggingface.co/spacematt/Qwen2.5 - Composite - Coder - 14B - Instruct)
- [spacematt/Qwen2.5 - Casual - Coder - 14B - Instruct](https://huggingface.co/spacematt/Qwen2.5 - Casual - Coder - 14B - Instruct)
- [spacematt/Qwen2.5 - Flow - Coder - 14B - Instruct](https://huggingface.co/spacematt/Qwen2.5 - Flow - Coder - 14B - Instruct)
- [spacematt/Qwen2.5 - Smooth - Coder - 14B - Instruct](https://huggingface.co/spacematt/Qwen2.5 - Smooth - Coder - 14B - Instruct)
- [spacematt/Qwen2.5 - Agile - Coder - 14B - Instruct](https://huggingface.co/spacematt/Qwen2.5 - Agile - Coder - 14B - Instruct)
- [spacematt/Qwen2.5 - CompositeFlow - Coder - 14B - Instruct](https://huggingface.co/spacematt/Qwen2.5 - CompositeFlow - Coder - 14B - Instruct)
- [spacematt/Qwen2.5 - Vibe - Coder - 14B - Instruct](https://huggingface.co/spacematt/Qwen2.5 - Vibe - Coder - 14B - Instruct)
- [spacematt/Qwen2.5 - Composite - 14B - Instruct](https://huggingface.co/spacematt/Qwen2.5 - Composite - 14B - Instruct)
- [spacematt/Qwen2.5 - Sharp - Coder - 14B - Instruct](https://huggingface.co/spacematt/Qwen2.5 - Sharp - Coder - 14B - Instruct)
- [spacematt/Qwen2.5 - Slick - Coder - 14B - Instruct](https://huggingface.co/spacematt/Qwen2.5 - Slick - Coder - 14B - Instruct)
- [spacematt/Qwen2.5 - Wicked - Coder - 14B - Instruct](https://huggingface.co/spacematt/Qwen2.5 - Wicked - 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
- model: spacematt/Qwen2.5-CompositeFlow-Coder-14B-Instruct
- model: spacematt/Qwen2.5-Casual-Coder-14B-Instruct
- model: spacematt/Qwen2.5-Smooth-Coder-14B-Instruct
- model: spacematt/Qwen2.5-Slick-Coder-14B-Instruct
- model: spacematt/Qwen2.5-Wicked-Coder-14B-Instruct
- model: spacematt/Qwen2.5-Agile-Coder-14B-Instruct
- model: spacematt/Qwen2.5-Channel-Coder-14B-Instruct
merge_method: model_stock
base_model: spacematt/Qwen2.5-Channel-Coder-14B-Instruct
normalize: true
int8_mask: true
dtype: bfloat16
đ License
This project is licensed under the apache - 2.0
license.
Property |
Details |
Base Models |
spacematt/Qwen2.5-Composite-Coder-14B-Instruct, spacematt/Qwen2.5-Casual-Coder-14B-Instruct, spacematt/Qwen2.5-Channel-Coder-14B-Instruct, spacematt/Qwen2.5-Flow-Coder-14B-Instruct, spacematt/Qwen2.5-Smooth-Coder-14B-Instruct, spacematt/Qwen2.5-Agile-Coder-14B-Instruct, spacematt/Qwen2.5-CompositeFlow-Coder-14B-Instruct, spacematt/Qwen2.5-Vibe-Coder-14B-Instruct, spacematt/Qwen2.5-Composite-14B-Instruct, spacematt/Qwen2.5-Sharp-Coder-14B-Instruct, spacematt/Qwen2.5-Slick-Coder-14B-Instruct, spacematt/Qwen2.5-Wicked-Coder-14B-Instruct |
Library Name |
transformers |
Tags |
mergekit, merge |
License |
apache - 2.0 |