Ziyang1060

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

HippoRAG

[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.

ListT5

official repository for ListT5

LLaMA-Factory-for-IR

Unify Efficient Fine-Tuning of 100+ LLMs

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

RAG-Retrieval

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT,Cross Encoder

RankAdapter

Code for paper "LLM-based expertise-driven doctor recommendation via adaptive prompt"

rStar

tevatron

Tevatron - A flexible toolkit for neural retrieval research and development.

Ziyang1060/RankAdapter

Code for paper "LLM-based expertise-driven doctor recommendation via adaptive prompt"

Ziyang1060/FlagEmbedding

Retrieval and Retrieval-augmented LLMs

Ziyang1060/HippoRAG

[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.

Ziyang1060/ListT5

official repository for ListT5

Ziyang1060/LLaMA-Factory-for-IR

Unify Efficient Fine-Tuning of 100+ LLMs

Ziyang1060/minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Ziyang1060/RAG-Retrieval

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT,Cross Encoder

Ziyang1060/rStar

Ziyang1060/tevatron

Tevatron - A flexible toolkit for neural retrieval research and development.