⚠️⚠️⚠️IMPORTANT⚠️⚠️⚠️ In its current state, this model DOES NOT perform very well with Mindcraft and can only do very rudimentary tasks. Still a very big step up from V2, it's able to parse commands correctly in the correct syntax, but appears unable to choose the right command for an action it wants to take (possibly fixable with a good profile). This model is a fine-tuned LoRA adapter built on top of LiquidAI/LFM2-700M.
It is designed for CPU inference or those who are GPU poor, requiring sub 1gb of memory to load the model at Q8 precision. The model is NOT compatible with Ollama, it is highly recommended to use LMStudio instead. Here is an example Mindcraft profile:

And an example Mindcraft keys.json:

This model was trained on the following datasets:

The training data is subject to the Andy 1.0 License

@misc{vonwerra2022trl,
  title        = {{TRL: Transformer Reinforcement Learning}},
  author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
  year         = {2020},
  journal      = {GitHub repository},
  publisher    = {GitHub},
  howpublished = {\url{https://github.com/huggingface/trl}}
}

@misc{liquidai_lfm2_700m,
  title        = {LFM2-700M},
  author       = {Liquid AI},
  year         = {2024},
  howpublished = {\url{https://huggingface.co/LiquidAI/LFM2-700M}}
}