Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.3-Coder

This model is a fine-tuned version of NQLSG-Qwen2.5-14B-MegaFusion-v9.3 designed to enhance C/C++ programming skills. Its capabilities in other domains may have regressed.

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 Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.3 as a base.

Models Merged

The following models were included in the merge:

• Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.3 + Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.3-coder-convos-2
• Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.3 + Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.3-coder-convos-1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.3
  - model: Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.3+Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.3-coder-convos-1
  - model: Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.3+Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.3-coder-convos-2
merge_method: model_stock
base_model: Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.3
dtype: bfloat16
tokenizer:
  source: "base"
parameters:
  int8_mask: true