modsysML — Human reinforcement learning (RLHF) framework for AI models. Evaluate and compare LLM outputs, test quality, catch regressions and automate.
GitHub Trending·
Originalartikel lesen bei GitHub TrendingHuman reinforcement learning (RLHF) framework for AI models. Evaluate and compare LLM outputs, test quality, catch regressions and automate. · Sprache: Python · Topics: ai, automation-framework, data-science, machinelearning, mlops, natural-language-processing · ⭐ 35 Stars
MITRE ATT&CK Kill Chain (1 Techniken)
Execution
Themen
aiautomation-frameworkdata-sciencemachinelearningmlopsnatural-language-processingnlp-machine-learningopen-sourceprompt-toolkitprompts