---
title: WVY Tiny Liquid LM
emoji: 🌊
colorFrom: gray
colorTo: indigo
sdk: gradio
sdk_version: 6.26.0
python_version: "3.12"
app_file: app.py
suggested_hardware: cpu-basic
short_description: Chat with a 3.31M-parameter custom liquid-style LM.
---

# WVY Tiny Liquid LM

A Hugging Face Space for the trained `TinyLiquidCausalLanguageModel` checkpoint in this repository.

## Model

- Parameters: 3,314,880
- Vocabulary: 8,000 BPE tokens
- Width: 192
- Blocks: 4
- Feed-forward hidden width: 512
- Causal depthwise convolution kernel: 5
- Context used by the chat app: 256 tokens
- Architecture: recurrent liquid-style state mixer + SwiGLU feed-forward layers
- Final fine-tuning loss: 0.1344
- Final fine-tuning perplexity: 1.1438

The Space loads the custom PyTorch architecture directly from `model.py`, restores `tiny_liquid_causal_lm.pt`, and uses the bundled `tokenizer.json`.

## Files

- `app.py` — Gradio chat UI and autoregressive generation
- `model.py` — exact custom model architecture used for the checkpoint
- `tiny_liquid_causal_lm.pt` — final fine-tuned checkpoint
- `tokenizer.json` — BPE tokenizer
- `model_config.json` — architecture configuration
- `training_summary.json` — training statistics
- `requirements.txt` — runtime dependencies