---
license: other
license_name: how-to-get-a-license-when-i-dont-want-to-die
license_link: LICENSE
datasets:
- mondk/Greetings-hi-for-train-Msh-v2
- tatsu-lab/alpaca
- databricks/databricks-dolly-15k
- teknium/OpenHermes-2.5
- m-a-p/Code-Feedback
- OpenAssistant/oasst1
- FreedomIntelligence/medical-o1-reasoning-SFT
- glaiveai/glaive-function-calling-v2
- openai/openai_humaneval
- HuggingFaceH4/no_robots
- open-thoughts/OpenThoughts-114k
- HuggingFaceH4/ultrachat_200k
- google-research-datasets/poem_sentiment
- CohereLabs/aya_dataset
- sentence-transformers/natural-questions
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 + hyperparameters
- `model_weights.pt` — trained PyTorch weights
- `tokenizer.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/Msh-Tiny-47M`](https://huggingface.co/mondk/Msh-Tiny-47M).

- `.model`: [`mondk/Msh-Tiny-47M-GGUF`](https://huggingface.co/mondk/Msh-Tiny-47M-GGUF)
---

my license: https://huggingface.co/mondk/see_upcoming_models/blob/main/LICENSE