metadata
license: other
license_name: how-to-get-a-license-when-i-dont-want-to-die
license_link: LICENSE
datasets:
- HuggingFaceH4/no_robots
- teknium/OpenHermes-2.5
- tatsu-lab/alpaca
language:
- en
pipeline_tag: text-generation
tags:
- from-scratch
- msh
- googlecolab
- pytorch
hi guys, im lazy to write, so this was written by claude, ty
This is my MSH-Tiny model before the redesign (you could say it's the original version, lol)
Files
config.json— architecture + hyperparametersmodel_weights.pt— trained PyTorch weightstokenizer.json— custom BPE tokenizer
How to run it
Use the included notebook You_can_still_run_it_directly_on_your_own_machine_if_it's_too_small.ipynb — open it in Google Colab, run all cells.
Looking for a ready-to-use format instead?
.safetensors:mondk/Safetensors.msh-tiny.gguf:mondk/GGUF.msh-tiny
my license: https://huggingface.co/mondk/see_upcoming_models/blob/main/LICENSE