metadata

language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - gguf
  - trl
  - sft
base_model: unsloth/tinyllama-bnb-4bit

This model is a work in progress, mainly created to test a cthulhu-fied data set. The plan is to train this model further, and eventually also make the data set public.

The data set itself is based on alpaca-cleaned, except all the replies have been re-written to sound like they were given by a cultist of Cthulhu. Only a subset of the data (10k entries) was used to train the first iteration of this model

Uploaded model

Developed by: theprint
License: apache-2.0
Finetuned from model : unsloth/tinyllama-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.