Deberta Python Packages

loralib

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

premove-itn

Premove ITN: context-aware inverse text normalization for English voice-agent transcripts.

oev

An 184M-parameter decision engine delivering calibrated distributions from one 22ms forward pass while matching models 2.3x its size.

director-ai

Real-time LLM hallucination guardrail — NLI + RAG fact-checking with opt-in claim-level streaming contradiction halt. Drop-in for any LLM backend.

backfire-kernel

Real-time LLM hallucination guardrail — NLI + RAG fact-checking with opt-in claim-level streaming contradiction halt. Drop-in for any LLM backend.

resonance-layer

Emotional intelligence layer for AI - detects emotion, tracks wellbeing, and gives any LLM the context to respond to how people actually feel.

bastion-prompt-protection

Lightweight prompt-injection detector built for AI agents, copilots, and LLM apps. Fast, local, calibrated.

director-ai-lite

Real-time LLM hallucination guardrail — NLI + RAG fact-checking with opt-in claim-level streaming contradiction halt. Drop-in for any LLM backend.

fastc

Unattended Lightweight Text Classifiers with LLM Embeddings

llama-index-postprocessor-bastion-guardrail

Lightweight prompt-injection detector built for AI agents, copilots, and LLM apps. Fast, local, calibrated.

sam-lora-lib

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"