Thanks to chargoddard for the original 22b model and merge script: https://huggingface.co/chargoddard/llama2-22b

This uses https://huggingface.co/Blackroot/FrankensteinsMonster-13B as a base, with https://huggingface.co/ehartford/WizardLM-33B-V1.0-Uncensored as the donor model.

This an experimental model and it sometimes forgets its context or says something nonsensical, but maybe some further fine tuning would smooth things out. This has less guardrails than my prior merge, https://huggingface.co/nkpz/llama2-22b-chat-wizard-uncensored

Took around 2 hours to merge with 32gb of ram and about 115gb of swap used.

Downloads last month
33
Safetensors
Model size
21.8B params
Tensor type
F32
·
FP16
·
Inference Examples
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.