> Canonical page: https://posttrainllm.com/learn/artifacts/byte-tinygpt

Buildable artifact · stage 1

# Byte-level TinyGPT

A readable ~0.8M-parameter transformer whose byte tokenizer, architecture, loss, and checkpoint format are all inspectable.

**Readiness**
 runnable lab

**Kind**
 model checkpoint

**Workload**
 light first; training duration is user-controlled

**Stage**
 Make a language model

## Artifact contract

A readable ~0.8M-parameter transformer whose byte tokenizer, architecture, loss, and checkpoint format are all inspectable.

This model checkpoint is classified as runnable lab. Workload guidance: light first; training duration is user-controlled.

## Build

Train the tiny preset on the bundled corpus.

## Modify

Change layers, heads, width, or context in the source-of-truth model config.

## Tune

Change learning rate, batch size, seed, or step budget one variable at a time.

## Prove

Inspect initial loss, tiny-overfit behavior, samples, and tensor inventory.

## Package

Keep a validated .tinygpt checkpoint with its exact config and corpus.

## CLI surface

- Run: posttrainllm train
- Run: posttrainllm inspect
- Run: posttrainllm validate

## How to read this dossier

This canonical page separates the retained repository decision from the material that informed it. A source may describe an external claim, historical measurement, local observation, or planned procedure; those evidence classes are not interchangeable. Follow the provenance links before reusing a number or method.

Status and disposition describe what PostTrainLLM retained when this record was indexed. They are not a live product promise, a newly run benchmark, or permission to restart historical work. Unknown or unmeasured fields remain unknown rather than being treated as zero.

To reuse the record, first name the exact claim you need and trace it to the linked source. Then check whether the original environment, model revision, data split, evaluator, hardware, and budget match the proposed use. If they do not, treat the record as a hypothesis or design reference and run the smallest fresh comparison that can falsify it. Preserve negative outcomes and regressions beside any improvement; a local win on one slice does not silently become a general capability claim.

## Source provenance

The normalized record comes from docs/learn/artifact-journey.json . The links below are the tracked evidence and explanatory sources preserved with the record.

- [python_ref/model.py ↗](https://github.com/PostTrainLLM/posttrainllm/blob/main/python_ref/model.py)
- [python_ref/train.py ↗](https://github.com/PostTrainLLM/posttrainllm/blob/main/python_ref/train.py)
- [data/examples/tiny-corpus.txt ↗](https://github.com/PostTrainLLM/posttrainllm/blob/main/data/examples/tiny-corpus.txt)
- [Train the tiny preset on the bundled corpus. ↗](https://posttrainllm.com/docs/guides/training_guide/)
- [Change layers, heads, width, or context in the source-of-truth model config. ↗](https://github.com/PostTrainLLM/posttrainllm/blob/main/configs/model.byte-tinygpt-v0.json)
- [Change learning rate, batch size, seed, or step budget one variable at a time. ↗](https://github.com/PostTrainLLM/posttrainllm/blob/main/configs/training.json)
- [Inspect initial loss, tiny-overfit behavior, samples, and tensor inventory. ↗](https://github.com/PostTrainLLM/posttrainllm/blob/main/tests/README.md)
- [Keep a validated .tinygpt checkpoint with its exact config and corpus. ↗](https://posttrainllm.com/docs/guides/model_guide/)

[Read the Markdown equivalent →](https://posttrainllm.com/learn/artifacts/byte-tinygpt.md)

Related evidence

- learning path [Make a language model](https://posttrainllm.com/learn/paths/foundations)

 Canonical record learning-artifact:byte-tinygpt