Skip to main content

Chat with Mr Chatterbox

Project description

llm-mrchatterbox

PyPI Changelog Tests License

Mr. Chatterbox is a language model trained from scratch by Trip Venturella using nanochat on a corpus of over 28,000 Victorian-era British texts published between 1837 and 1899, made available by the British Library.

This LLM plugin vendors enough of nanochat to get the model to work, also borrowing some details from Trip's mr_chatterbox HuggingFace Space . You can also chat with the model using that Space in your browser.

Installation

Install this plugin in the same environment as LLM.

llm install llm-mrchatterbox

Usage

The first time you run a prompt the ~2GB model will be downloaded to your machine.

llm -m mrchatterbox 'hello good sir'

Chat with the model using the chat command:

llm chat -m mrchatterbox

The cached model is stored in the path revealed by this command:

llm mrchatterbox path

On a Mac that folder is:

~/Library/Application Support/io.datasette.llm/mrchatterbox

You can delete the model file using this command:

llm mrchatterbox delete-model

Development

To set up this plugin locally, first checkout the code. Run the tests like this:

cd llm-mrchatterbox
uv run pytest

To run prompts through the model use:

uv run llm -m mrchatterbox 'hello good sir'

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

llm_mrchatterbox-0.1.tar.gz (35.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

llm_mrchatterbox-0.1-py3-none-any.whl (37.9 kB view details)

Uploaded Python 3

File details

Details for the file llm_mrchatterbox-0.1.tar.gz.

File metadata

  • Download URL: llm_mrchatterbox-0.1.tar.gz
  • Upload date:
  • Size: 35.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for llm_mrchatterbox-0.1.tar.gz
Algorithm Hash digest
SHA256 61a051d0e2dc90174cd6931a982636f7cf1e4c23bc560772b7efceeb0d9305f1
MD5 f765022f2b37d8222a4e902dacd1fac4
BLAKE2b-256 9612eeda5f857d15399d19b23485b4ff6473e2a97af4c379a9f0f23d5392f09d

See more details on using hashes here.

Provenance

The following attestation bundles were made for llm_mrchatterbox-0.1.tar.gz:

Publisher: publish.yml on simonw/llm-mrchatterbox

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file llm_mrchatterbox-0.1-py3-none-any.whl.

File metadata

  • Download URL: llm_mrchatterbox-0.1-py3-none-any.whl
  • Upload date:
  • Size: 37.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for llm_mrchatterbox-0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 909f443c1c04e518593c3ae32c9108b1a25b9c12ccc5fc6cb56ec85809ff0a06
MD5 d0cf90fa05f08d16136575f55dbf36d2
BLAKE2b-256 ee8bd92747a165ace4848ba4a158aef05dc679a5b3e6ccfa7ae3097506cb7181

See more details on using hashes here.

Provenance

The following attestation bundles were made for llm_mrchatterbox-0.1-py3-none-any.whl:

Publisher: publish.yml on simonw/llm-mrchatterbox

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page