Lotus 12b encoded into 4 bit as named. The first one I am uploading has true sequential and act order but no group size (full rank)
You can likely use it with textgen-ui or have a go at my v1/v2 supporting version
https://github.com/Ph0rk0z/text-generation-webui-testing/tree/DualModel
get tokenizers from pythia-12b or lotus-12b here on HF
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.