---
license: apache-2.0
language:
- en
- zh
base_model:
- Qwen/Qwen2.5-14B
- Qwen/Qwen2.5-14B-Instruct
- Qwen/Qwen2.5-14B-Instruct-1M
- tanliboy/lambda-qwen2.5-14b-dpo-test
- arcee-ai/SuperNova-Medius
- arcee-ai/Virtuoso-Small-v2
- Azure99/Blossom-V6-14B
- Qwen/Qwen2.5-Coder-14B
- Qwen/Qwen2.5-Coder-14B-Instruct
- deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
- huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2
pipeline_tag: text-generation
tags:
- merge
---
![image/png](/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F64e174e202fa032de4143324%2Fzx2LWe9rip2AVr76BH4Er.png)
# Qwen2.5-14B-YOYO-V4-p3

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

This is the **final preview version** of the fourth-generation Qwen YOYO series model, and it is currently my favorite iteration. 

Aside from context length, it is identical to **Qwen2.5-14B-YOYO-V4** in all other aspects. 

The upcoming official release will not only expand the context length to 1M tokens but also disclose the complete merge recipe. 

Stay tuned for more updates!