llm-pig 🐷
llm-pig is a comprehensive Python library designed for advanced LLM perplexity analysis, covering both token-level micro inspection and macro-level dataset evaluation. It provides clean, interactive HTML visualizations powered by Pandas and Plotly.
Features
- Token-Level Curve Analysis: Interactive line charts tracking token uncertainty across a prompt or document.
- Cascading Bar Charts: Sorted bar representations highlighting peak perplexity tokens.
- SHAP-Style Text Highlights: Individual and comparative multi-model text highlights using dynamic color gradient scales.
- Macro Statistical Distribution: Comprehensive Boxplots and Violin Plots summarizing model performance across large test datasets (including Min, Q1, Median, Q3, and Max metrics).
Installation
Install the package via pip:
pip install llm-pig
1 maintainer
Metadata
1 maintainer
Release files for llm-pig 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| llm_pig-0.1.0.tar.gz | 7.8 kB | Without provenance | Details for llm_pig-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| llm_pig-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for llm_pig-0.1.0-py3-none-any.whl |
Total release size: 20.2 kB
Release files / llm_pig-0.1.0.tar.gz
| Download URL | llm_pig-0.1.0.tar.gz |
|---|---|
| Size | 7.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9351e4b9caf23ca16d491e975f167928fdf1286f42878b291a53b058440526e0
|
|
BLAKE2b-256 checksum How to use checksums |
2f9a2b5b101da12d83ee5893c58a7346e4e6a9f74df7b90e08ed481a27d5a99f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/2.4.3 CPython/3.14.6 Windows/11
|
Release files / llm_pig-0.1.0-py3-none-any.whl
| Download URL | llm_pig-0.1.0-py3-none-any.whl |
|---|---|
| Size | 12.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4aca80829f19a0fa6f689c5b3f69d6388e145759b1c7e734828bcfe68307c6ac
|
|
BLAKE2b-256 checksum How to use checksums |
dc5f6c44c6aa9340111412192e9961f2716336d30e6ebbc337b24ac098ef143b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/2.4.3 CPython/3.14.6 Windows/11
|
Security for llm-pig 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
