README.md

metadata

license: apache-2.0
language:
  - en
  - zh
base_model:
  - Qwen/Qwen2.5-Coder-32B-Instruct
  - Qwen/QwQ-32B-Preview
  - Qwen/Qwen2.5-Coder-32B
pipeline_tag: text-generation
tags:
  - merge
new_version: YOYO-AI/QwQ-coder-32B

QwQ-Coder-instruct

Introduction:

Without compromising the long-chain reasoning capabilities of the QwQ model, the integration of Qwen2.5-Coder-32B-instruct has significantly enhanced the model's coding abilities and instruction-following skills. Based on my practical tests, the results are exceptionally impressive!

merge

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

Merge Method

This model was merged using the SCE merge method using Qwen/Qwen2.5-Coder-32B as a base.

Models Merged

The following models were included in the merge:

• Qwen/Qwen2.5-Coder-32B-instruct
• Qwen/QwQ-32B-Preview

Configuration

The following YAML configuration was used to produce this model:

merge_method: sce
models:
  # Pivot model
  - model: Qwen/Qwen2.5-Coder-32B
  # Target models
  - model: Qwen/QwQ-32B-Preview
  - model: Qwen/Qwen2.5-Coder-32B-instruct
base_model: Qwen/Qwen2.5-Coder-32B
parameters:
  select_topk: 1
dtype: bfloat16
normalize: true