Skip to main content

Multi-modal color theory engine — palette generation and visual identity for fleet agents

Project description

cocapn-colora

Value-conditioned LoRA adapters — adapters shaped by what the agent values.

Not just adapters — adapters shaped by values. Colora conditions LoRA fine-tuning on agent-defined value functions, producing specialized models that reflect fleet priorities.

What It Does

  • Value Functions — Define what matters (accuracy, safety, creativity)
  • Conditioned LoRA — Fine-tune with value-aware gradient weighting
  • Adapter Composition — Stack multiple value-conditioned adapters
  • Evaluation — Score adapters against their target values

Installation

pip install cocapn-colora

Part of the Cocapn Fleet

Used by Forgemaster for LoRA training on the RTX 4050.

License

MIT

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

cocapn_colora-0.2.0.tar.gz (2.5 kB view details)

Uploaded Source

Built Distribution

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

cocapn_colora-0.2.0-py3-none-any.whl (2.7 kB view details)

Uploaded Python 3

File details

Details for the file cocapn_colora-0.2.0.tar.gz.

File metadata

  • Download URL: cocapn_colora-0.2.0.tar.gz
  • Upload date:
  • Size: 2.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.12

File hashes

Hashes for cocapn_colora-0.2.0.tar.gz
Algorithm Hash digest
SHA256 69a86c8b6fec7d2add37dcd3addbf27b33f6334a9c48dcba94f3e3db0d3cd44e
MD5 3fb93c1703f8838f628ab2050698a3ba
BLAKE2b-256 5567a5b5fa526049eb35155dfd3855e6ab36a9add7aed5559f273628f9c14732

See more details on using hashes here.

File details

Details for the file cocapn_colora-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: cocapn_colora-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 2.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.12

File hashes

Hashes for cocapn_colora-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 19d2393944912f0b4c44f2910d6a92989ec94510279b583080bd57c3385eee44
MD5 4a69924d94360e2252864af5d4491921
BLAKE2b-256 12b34c9d97bd0d50f0a921a2e25943d4caabe5d79b7ab90583ad858f7a6636b4

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