TrustyAI's repositories
trustyai-explainability
TrustyAI Explainability Toolkit
trustyai-explainability-python
Python bindings for TrustyAI's explainability library
trustyai-explainability-python-examples
Examples for the Python bindings for TrustyAI's explainability library
trustyai-service-operator
TrustyAI's Kubernetes operator
trustyai-detoxify
Algorithms and tools for detecting and fixing hate speech, abuse and PII disclosure (HAP) in text generated by LLMs
odh-trustyai-demos
Demos showcasing TrustyAI's capabilities within Open Data Hub.
trustyai-kserve-explainer
KServe TrustyAI explainer
trustyai-ood
Library for out-of-distribution detection for models
trustyai-service
TrustyAI service providing cloud-native fairness metrics and explainability
trustyai-explainability-sandbox
TrustyAI space for experimentation and PoCs
trustyai-explainability.github.io
TrustyAI main documentation
fms-guardrails-orchestrator
🚀 Guardrails orchestration server for application of various detections on text generation input and output.
guardrails-detectors
This repository is intended to provide a collection of detectors that are supported by the TrustyAI team in the context of the FMS Guardrails Orchestrator project
lm-eval-tasks
Repo for lm-eval tasks built by the TrustyAI team
reference
Unofficial TrustyAI documentation and guides
trustyai-console
Web console for TrustyAI Explainability Service.
trustyai-detoxify-sft
Guardrailing LLMs during training via HF SFT Trainer and TrustyAI Detoxify
trustyai-ig
Library for explaining the relationship between input text and outputs in LLMs
trustyai-pipeline-blocks
Collection of TrustyAI Data Science Pipeline blocks
trustyai-service-operator-ci
🤖 Contains automatically-generated manifests for TrustyAI+ODH CI jobs 🤖
trustyai-tests
TrustyAI functional integration tests.
vllm_emulator
Tiny vLLM emulation server for integration testing without GPU