This modelfile is the LoRA adapter for Andy-3.6
Note:
Andy-4 is right around the corner, and will be released before the end of April, if you are considering fine tuning off of this model I would wait until the higher performance Andy-4 model gets released.
Why this exists
This Repo exists because I wanted to make Andy-3.6 fully open-source, via Unsloth, you are able to continue fine tuning where I left off, so if you made your own dataset, you can continue tuning Andy-3.6 for your exact use case.
What if I fine tune off of Andy-3.6?
If you fine tune Andy-3.6 on your dataset, my dataset, or any other dataset, you have to provide credit to me for making the base model, which is Andy-3.6, if you wish, you may call the model Andy-3.6-base
Why would I want to fine tune off of Andy-3.5?
Andy-3.6 has a significant amount of knowledge regarding Minecraft and MindCraft, but not unlimited. Andy-3.6 can be trained further on Minecraft knowledge to make the model better, and if you strive for maximum efficiency, it would be best to continue fine-tuning a model based on similar data to help it.
What should I call my model if I do tune it?
You may name it whatever you'd like, but if I may suggest, I would recommend a name that clearly references the fact it originated from Andy-3.6.
If you'd like an example, if I trained Andy-3.6 on speedrunning tactics, I would call the model Andy-3.6-Speedrun or something similar.
- Downloads last month
- 46
Model tree for Sweaterdog/Andy-3.6-LoRA
Base model
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B