NandhaKishorM/vegaml
Typed decisions from a frozen language model and a small physics engine: calibrated probabilities, conformal sets, 73k context, images.
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
Typed decisions from a frozen language model and a small physics engine. You give it a state and a question whose answer type is fixed in advance; it returns a value your code can use directly: a choice, a 0 to 1 score, or the probability that a statement is true. Each carries a calibrated probability, a conformal answer set and an explicit abstain flag. vega-U: one 14.3M engine, any frozen reader, from 0.8B to 27B · 73,728-token context · images · runs on your own hardware. No text is generated anywhere in the path. The default model. Four frozen readers behind one byte-identical 14.3M engine; the readers marked "attached cold" were never part of the engine's training and scored highest anyway. The full per-source board, the method and the caveats are in docs/vega-u.md; the full per-source board is in the Benchmarks section below. [](https://colab.research.google.com/drive/1ZxSEe4-oyfo8ePKiAgbehv5I1Rh3F7O?usp=sharing) Inference on a single T4,…
Read the full README ↗ · Preview checked 2026-10-31T18:54:25.102Z
Inside the original README — Document outline
- vegaml
- Quick start
- Attach your own model, without retraining anything
- Devices
- Two readouts, one set of features
- Images
- Audio
- 73,728-token context
- Answer types
- vega-U: one engine, any reader
- Beyond the Python API
- The earlier checkpoints: classic vega in two sizes
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Typed decisions from a frozen language model and a small physics engine: calibrated probabilities, conformal sets, 73k context, images.
Repository facts
- Owner
- NandhaKishorM
- Primary language
- Python
- Stars
- 243
- Forks
- 30
- Open issues + pull requests
- 6
- License
- Apache-2.0
- Archived
- No
- Default branch
- main
- Created
- 2026-10-09T17:45:54.000Z
- Last push
- 2026-10-16T06:56:17.000Z
Topics and intended use
No topics were included in the latest source metadata.
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-16T12:08:52.409Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer