Metadata-Version: 2.5
Name: llmdbg
Version: 0.0.3a1
Summary: A debugger for stepping through LLM layers and interpreting internal representations.
License-Expression: MIT
License-File: LICENSE
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Topic :: Software Development :: Debuggers
Requires-Python: >=3.10
Requires-Dist: gb10-load-llm==0.1.2
Description-Content-Type: text/markdown

# llmdbg

`llmdbg` is an early-stage debugger for stepping through language-model layers
and presenting human-readable interpretations of internal vectors. It speaks
the [Debug Adapter Protocol](https://microsoft.github.io/debug-adapter-protocol/)
so editor integrations can use a standard debugger UI.

The current prototype includes real GPT-2 Small loading, layer-state capture,
logit-lens interpretations, and a VS Code debug extension. A deterministic
built-in trace remains available when no model is configured.

```console
pip install --pre llmdbg
llmdbg --version
```

## VS Code prototype

Build and install the extension:

```console
cd vscode-extension
npm install
npm run package
code --install-extension llmdbg-0.0.1.vsix
```

Open the repository in VS Code, select **llmdbg: Demo model** in **Run and
Debug**, and press **F5**. On first use, the extension creates a private Python
environment in VS Code's extension storage. It does not install anything into
the workspace. Use **Step Over** to advance one layer at a time.

For GPT-2 Small, add `"model": "openai-community/gpt2"` and a `prompt` to the
launch configuration. The first run downloads the model into the normal
Hugging Face cache.

## License

MIT
