rizla-17 / README.md
rizla's picture
Update README.md
cb2b865 verified
|
raw
history blame
706 Bytes
metadata
license: cc-by-nc-nd-4.0
base_model:
  - mistralai/Mixtral-8x7B-Instruct-v0.1
tags:
  - dpo
  - merge
  - mergekit

rizla been cooking while singing

This is an experimental model that I made by merging two 2expmixtrals The mergekitty is a tool that lets me mix and match different models into one big model, keeping all the smarts and skills of the original models. The llama70b is a huge language model that can make words for all kinds of things and ways, based on the GPT-4 thingy.

The merged model has 17 billion parraraameters and was made to run on 8gb of ram minimum in q3KL gguf.

Merge me baby one more time

Sending this contraption out straight to mergeland, wwhheeeeeeeeeeeee LFG πŸš€