Qwen2.5-YOYO
Collection
5 items
•
Updated
•
2
Qwen2.5-YOYO Fourth-Gen Model Officially Released!
Qwen2.5-14B-YOYO-1005 is a merged language model created by combining Qwen2.5-14B and Qwen2.5-14B-Instruct using the della merging method. this model synthesizes the complementary strengths of its parent models to achieve a versatile balance between general-purpose reasoning and task-specific adaptability.
During model merging, Qwen2.5-14B-YOYO-1005 and Qwen2.5-14B-YOYO-1010 utilized different densities of Qwen2.5-14B-instruct.
I will explore different merging densities to investigate how they impact the model's performance.
- Downloads last month
- 82
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-1005
Base model
Qwen/Qwen2.5-14B
Finetuned
Qwen/Qwen2.5-14B-Instruct