Edit model card

Gemma-Ko

Quantized model from: Gemma Ko
Original Gemma Model Page: Gemma

This model card corresponds to the 7B base version of the Gemma-Ko model.

Resources and Technical Documentation:

Terms of Use: Terms

Downloads last month
3
Safetensors
Model size
1.82B params
Tensor type
I32
·
FP16
·
Inference API
This model can be loaded on Inference API (serverless).

Collection including ghost613/gemma-ko-7b-AWQ