genta-tech
/

dukunlm-7b-awq-st

Text Generation

Inference Endpoints

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Edit model card

This model is quantized version of azale-ai/DukunLM-7B-V1.0-Uncensored

Downloads last month: 1

Safetensors

Model size

1.13B params

Tensor type

I32

·

FP16

·