---
license: apache-2.0
language:
- en
- zh
base_model:
- Qwen/Qwen2.5-14B-Instruct
- arcee-ai/Virtuoso-Small-v2
- deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
- huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2
- Qwen/Qwen2.5-Coder-14B
- Qwen/Qwen2.5-Coder-14B-Instruct
pipeline_tag: text-generation
tags:
- merge
---
![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e174e202fa032de4143324/zx2LWe9rip2AVr76BH4Er.png)
# Qwen2.5-14B-YOYO-V4-p2

*[Qwen2.5-YOYO Fourth-Gen Model Officially Released!](https://huggingface.co/YOYO-AI/Qwen2.5-14B-YOYO-V4)*

The letter "p" stands for "preview," indicating the preview version of the fourth-generation Qwen-YOYO series model. 

Three preview versions will be released, each utilizing distinct merging methodologies. 

The best-performing model will be selected and expanded to support a 1 million-token context length, which will then be finalized as the official release. Stay tuned for updates!