Skip to main content

An extension for using llama-guard with aiconfig

Project description

Using LLama-Guarde for model parsing with AIConfig

We are prioritizing the Python library Usage

Part 1: Update and test this extention

If you are not testing locally (just using the published extension), ignore this and go to Part 2

  1. From the aiconfig/HuggingFaceTransformers, run this command: pip install build && cd python && python -m build && pip install dist/*.whl
  2. After you're done testing, be sure to delete the generated folder(s) in the aiconfig/HuggingFaceTransformers dir. It'll probalby look something like python/dist and python/<package_name>.egg-info

Part 2: Importing and using this extension

  1. Import whatever outputs pip gives from last command. For now it's import text-generation but this may change in the future
  2. In code, add all the relevant model parsers that you want to use from this extension to the registry: ModelParserRegistry.register_model_parser(HuggingFaceTextGenerationTransformer()). You can read the docstrings under ModelParserRegistry class for more info

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

aiconfig_extension_llama_guard-0.0.2.tar.gz (5.7 kB view details)

Uploaded Source

Built Distribution

File details

Details for the file aiconfig_extension_llama_guard-0.0.2.tar.gz.

File metadata

File hashes

Hashes for aiconfig_extension_llama_guard-0.0.2.tar.gz
Algorithm Hash digest
SHA256 0bd689b8c1f7072a4c9f5384665b5407ae32e48bba22fe46ccb79bda7fe2d105
MD5 82d8fde3c42ce5acac2b906760eb7109
BLAKE2b-256 d591529b7ed1d8d494491cba608059ac0a57b93ee02c8ca576bb4b049adbfac0

See more details on using hashes here.

File details

Details for the file aiconfig_extension_llama_guard-0.0.2-py3-none-any.whl.

File metadata

File hashes

Hashes for aiconfig_extension_llama_guard-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 d5be4574e8651a728e7f8b6a75a6d9ac2498716c1de1b8e9279f5759eb2df7fc
MD5 9aad1239ce90532ce1ffeb3c9b01566c
BLAKE2b-256 243cfc12f9afbd8cc7a0bfc4476dffb86e2cf20f7e2ff13072d639ffaa4176ef

See more details on using hashes here.

Supported by

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