Skip to main content

Adam who? Your next PyTorch optimiser can be a cutting-edge LLM...

Project description

GradGPT

Adam who? Your next PyTorch optimiser can be a cutting-edge LLM...

snapshot of the system prompt for GradGPT

Demo video

thumbnail

How to use it in 1-2-3

  • Install this package from PyPI
pip install gradgpt
  • Import it
import gradgpt
  • You can now use it like any other PyTorch optimiser!
optimiser = gradgpt.GradGPT(llm="gpt-5", llm_provider="openai")
# is a torch.optim.Optimizer

Disclaimer: Let it be on the record that I said you can, not you should.

Contributions

You can try to open a PR on GitHub, but no guarantee of merge or even review.

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

gradgpt-0.1.5.tar.gz (4.9 kB view details)

Uploaded Source

Built Distribution

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

gradgpt-0.1.5-py3-none-any.whl (5.3 kB view details)

Uploaded Python 3

File details

Details for the file gradgpt-0.1.5.tar.gz.

File metadata

  • Download URL: gradgpt-0.1.5.tar.gz
  • Upload date:
  • Size: 4.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.5

File hashes

Hashes for gradgpt-0.1.5.tar.gz
Algorithm Hash digest
SHA256 e9d45c96347bc361931c9f62b389aef0f81c3aff8d3d7cf3234dbbd138015f9f
MD5 c18326040bbac252a6a03af1b4ae1229
BLAKE2b-256 692903bfe38539d044e248055fe19c86478d61a10c878e33ee64bc8db587fe82

See more details on using hashes here.

File details

Details for the file gradgpt-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: gradgpt-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 5.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.5

File hashes

Hashes for gradgpt-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 84f7ad531bc0502ebdae0fd99f85b23cc064f400ae81d6b1ab22abda4ceee75d
MD5 549a67aa512a7e0d57185e5521092e0f
BLAKE2b-256 a60b603f03bafb20a35ab1b1f2e9996e32a3282bc69780b426b8f61827f9e24e

See more details on using hashes here.

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