Tiefighter finetune of LLaMa2-13b from KoboldAI team.

Updated 8 months ago

No models have been pushed.

Readme

LLaMA2-13B-Tiefighter

Description from Huggingface

Tiefighter is a merged model achieved trough merging two different lora’s on top of a well established existing merge. To achieve this the following recipe was used:

  • We begin with the base model Undi95/Xwin-MLewd-13B-V0.2 which is a well established merged, contrary to the name this model does not have a strong NSFW bias.
  • Then we applied the PocketDoc/Dans-RetroRodeo-13b lora which is a finetune on the Choose your own Adventure datasets from our Skein model.
  • After applying this lora we merged the new model with PocketDoc/Dans-RetroRodeo-13b at 5% to weaken the newly introduced adventure bias.
  • The resulting merge was used as a new basemodel to which we applied Blackroot/Llama-2-13B-Storywriter-LORA and repeated the same trick, this time at 10%.

Application

The Tiefighter model is an amazing AI language tool perfect for roleplayin’. It’s great at following instructions and keeping track of what’s going on, so your story flows smoothly no matter how complex. Plus, it has great balance between formal and casual style in its writing, making it versatile across genres like sci-fi, fantasy, and modern drama.

This model is also amazing at text generation. It generates well-written content on all sorts of topics without sounding robotic, patronizing or too formal. I’m using it for my daily routines and it generates the most human-like texts without any prompt-engineering.