Edit model card

Yi-6B-200K - AWQ

This is a quantized (AWQ) version of Yi-6B-200K.

For more information about the model, see the original page.

It was quantized in the same way as the Yi-34B-200K: more information about it - here.

Downloads last month
3
Safetensors
Model size
1.27B params
Tensor type
I32
·
FP16
·
Inference API (serverless) has been turned off for this model.

Quantized from