Kudzu-8B / README.md
lodrick-the-lafted's picture
Create README.md
3fe4a14 verified
metadata
license: apache-2.0
base_model:
  - lodrick-the-lafted/Olethros-8B
  - lodrick-the-lafted/Limon-8B
  - lodrick-the-lafted/Rummage-8B
  - cgato/L3-TheSpice-8b-v0.8.3
  - unsloth/llama-3-8b-Instruct
  - Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total
library_name: transformers
tags:
  - mergekit
  - merge

Kudzu-8B

Fresh out of the mergekit-evolve kitchen, this is a merge model between:

Used wmdp as the scoring method for evolve. In my limited testing, it has not done the usual Llama-3 "Ahaha!" interjections while retaining a good portion of the intelligence. There are several ablated models in the mix so don't be surprised if it gives you what you ask for.