Generated from unsloth SimPO_colab_notebook.ipynb

https://colab.research.google.com/drive/1qHgk-YRz4pQHKER2QNjMXHgsERKyz8dF#scrollTo=ti7ZnQOY6s0O

How to use?

ollama run hf.co/chenhaodev/qwen-mini-simpo-gguf

Expected Output

check difference between this model vs qwen2.5-0.5b on the dataset https://huggingface.co/datasets/trl-lib/ultrafeedback_binarized/viewer/default/train?views%5B%5D=train&row=0

Downloads last month
5
GGUF
Model size
494M params
Architecture
qwen2
Hardware compatibility
Log In to view the estimation

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support