pogo-lm

Pogo LM — 4.8M

Pogo Spark is a 4,805,280-parameter decoder-only language model trained from scratch on an M1 Pro. It is a narrow, original cartoon-repair character model, not a general-purpose assistant.

This repository contains the selected MLX inference checkpoint from character training step 300, plus its exact tokenizer, config, checkpoint metadata, and the fixed behavior prompts used during the local run.

Files

• checkpoint.npz — MLX weights
• checkpoint.json — model geometry and checkpoint integrity metadata
• tokenizer.json — 4,096-token byte-level BPE
• config.json — inference/training geometry
• evaluation.jsonl — fixed local behavior prompts

Usage

These are custom MLX weights, not a Transformers or GGUF model. Use the training/inference code from DDDD-433/pogo-lm:

git clone https://github.com/DDDD-433/pogo-lm
cd pogo-lm
uv sync --python 3.12

# Download the five files from this Hub repo into ./model/
uv run pogo-generate \
  --config model/config.json \
  --tokenizer model/tokenizer.json \
  --checkpoint model/checkpoint.npz \
  --prompt '<|bos|> <|user|> Can you help me fix a wobbly paper rocket? <|assistant|>' \
  --temperature 0 --top-k 1

Training and limitations

The base stage ran for 12,000 steps on TinyStories, PersonaChat, and original Pogo data. The selected character checkpoint passed 8/8 fixed local behavior checks under greedy decoding. That is a regression check, not a safety certification or a general benchmark.

The corpus policy deliberately excludes named-franchise character data and scraped scripts. Source details and licenses are documented in the GitHub repository. The base corpus includes TinyStories, which is licensed under CDLA-Sharing-1.0; review upstream terms before redistributing the weights.