image/png

Qwen2.5-14B-YOYO-V4-p2

Qwen2.5-YOYO Fourth-Gen Model Officially Released!

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!

Downloads last month
68
Safetensors
Model size
14.8B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for YOYO-AI/Qwen2.5-14B-YOYO-V4-p2