Pythia 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
- Downloads last month
- 13
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.