Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A ~9M parameter LLM that talks like a small fish.
| Date | Stars |
|---|---|
| 2026-07-31 | 3308 |
| 2026-08-03 | 3308 |
| 2026-08-04 | 3311 |
| 2026-08-06 | 3311 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center"> <img src="assets/guppy.png" alt="GuppyLM" width="400"/> </p> <h1 align="center">GuppyLM</h1> <p align="center"><em>A ~9M parameter LLM that talks like a small fish.</em></p> <p align="center"> <a href="https://huggingface.co/datasets/arman-bd/guppylm-60k-generic"><img src="https://img.shields.io/badge/🤗_Dataset-guppylm--60k-blue" alt="Dataset"/></a> <a href="https://huggingface.co/arman-bd/guppylm-9M"><img src="https://img.shields.io/badge/🤗_Model-guppylm--9M-orange" alt="Model"/></a> <a href="https://github.com/arman-bd/guppylm/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-MIT-green" alt="License"/></a> <br/> <a href="https://colab.research.google.com/github/arman-bd/guppylm/blob/main/train_guppylm.ipynb"><img src="https://img.shields.io/badge/Train_in-Colab-F9AB00?logo=googlecolab" alt="Train"/></a> <a href="https://colab.research.google.com/github/arman-bd/guppylm/blob/main/use_guppylm.ipynb"><img src="https://img.shields.io/badge/Chat_in-Colab-F9AB00?logo=googlecolab" alt="Chat"/></a> <br/> <a href="https://www.linkedin.com/pulse/build-your-own-language-model-5-minutes-i-made-mine-hossain--supif/"><img src="https://img.shields.io/badge/Article-LinkedIn-0A66C2?logo=linkedin" alt="LinkedIn Article"/></a> <a href="https://arman-bd.medium.com/build-your-own-llm-in-5-minutes-i-made-mine-talk-like-a-fish-e20c338a3d14"><img src="https://img.shields.io/badge/Article-Medium-000000?logo=medium" alt="Medium Article"/></a> <br/><br/> <a href="https://arman-bd.github.io/guppylm/"><img src="https://img.shields.io/badge/Try_in-Browser-64ffda?style=for-the-badge&logo=webassembly&logoColor=white" alt="Browser Demo"/></a> </p> --- > **This project exists to show that training your own language model is not magic.** > No PhD required. No massive GPU cluster. One Colab notebook, 5 minutes, and you have a working LLM that you built from scratch — data generation, tokenizer, model architecture, training loop, and inference. If you can run a notebook, you can train a language model. > > It won't produce a billion-parameter model that writes essays. But it will show you exactly how every piece works — from raw text to trained weights to generated output — so the big models stop feeling like black boxes. --- ``` You> hi guppy Guppy> hi there. i just found a nice spot near the rock. the temperature feels nice. You> are you hungry Guppy> yes. always yes. i will swim to the top right now. i promise to eat all of it. You> do you like bubbles Guppy> i love bubbles. they make the water feel slightly different. You> what is the meaning of life Guppy> food. the answer is always food. You> tell me a joke Guppy> what did the fish say when it hit the wall. dam. You> do you love me Guppy> you're my favorite big shape. my mouth are happy when you're here. You> goodnight guppy Guppy> ok sleep time. i was following a bubble but now i'll stop. goodnight tank. goodnight water. ``` --- ## What is GuppyLM? GuppyLM is a tiny language model that pretends to be a fish named Guppy. It speaks in short, lowercase sentences about water, food, light, and tank life. It doesn't understand human abstractions like money, phones, or politics — and it's not trying to. It's trained from scratch on 60K synthetic conversations across 60 topics, runs on a single GPU in ~5 minutes, and produces a model small enough to run in a browser. --- ## Architecture | | | |---|---| | **Parameters** | 8.7M | | **Layers** | 6 | | **Hidden dim** | 384 | | **Heads** | 6 | | **FFN** | 768 (ReLU) | | **Vocab** | 4,096 (BPE) | | **Max sequence** | 128 tokens | | **Norm** | LayerNorm | | **Position** | Learned embeddings | | **LM head** | Weight-tied with embeddings | Vanilla transformer. No GQA, no RoPE, no SwiGLU, no early exit. As simple as it gets. --- ## Personality Guppy: - Speaks in short, lowercase sentences - Experiences the world through water, temperature, light, vibrations, and foo
Excerpt of 8,539 characters
Read on GitHub
Arman Hossain
21
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9f871073e39b82b6, llm:description: 'A ~9M parameter LLM that talks like a small fish.' (repo description)
matched fp:9f871073e39b82b6, llm:description: 'A ~9M parameter LLM that talks like a small fish.' (repo description)
matched fp:9f871073e39b82b6, llm:description: 'A ~9M parameter LLM that talks like a small fish.' (repo description)