tigerlab-ai/tiger
Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)
TigerRAG implements multi-stage retrieval strategies (EBR, RAG, GAR) with FAISS indexing and BERT embeddings, while TigerTune provides a Python SDK for fine-tuning generative and classification models like Llama2 and DistilBERT. TigerArmor adds quantitative safety measurement with standardized metrics and evaluation datasets for LLM risk assessment, and TigerDA enables generation-based data augmentation using instruction-tuned GPT2 with sampling-based decoding.
401 stars. No commits in the last 6 months.
Stars
401
Forks
27
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Dec 02, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/tigerlab-ai/tiger"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LearningCircuit/local-deep-research
Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports...
NVIDIA-AI-Blueprints/rag
This NVIDIA RAG blueprint serves as a reference solution for a foundational Retrieval Augmented...
Denis2054/RAG-Driven-Generative-AI
This repository provides programs to build Retrieval Augmented Generation (RAG) code for...
0verL1nk/PaperSage
📚 AI-powered research reading workbench. Project-based paper Q&A with Hybrid RAG, multi-agent...
RapidFireAI/rapidfireai
RapidFire AI: Rapid AI Customization from RAG to Fine-Tuning