Chunhui Shi's repositories
smart-compute
AI for big data materials
awesome-database-learning
A list of learning materials to understand databases internals
EigenFold
EigenFold: Generative Protein Structure Prediction with Diffusion Models
faiss
A library for efficient similarity search and clustering of dense vectors.
fastapi
FastAPI framework, high performance, easy to learn, fast to code, ready for production
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.
FATE
An Industrial Grade Federated Learning Framework
FATE-Board
FATE's Visualization Toolkit
FATE-Builder
A release packing tool for FATE
FATE-Flow
Solution for deploying and managing end-to-end federated learning workflows
FATE-LLM
Federated Learning for LLMs.
FederatedGPT-Shepherd
Shepherd: A lightweight, foundational framework enabling federated instruction tuning for large language models
fedlearner
A multi-party collaborative machine learning framework
gramine
A library OS for Linux multi-process applications, with Intel SGX support
KubeFATE
Manage federated learning workload using cloud native technologies.
langchain
⚡ Building applications with LLMs through composability ⚡
llama-cpp-python
Python bindings for llama.cpp
llama_index
LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data.
Megatron-DeepSpeed
Ongoing research training transformer language models at scale, including: BERT & GPT-2
milvus
A cloud-native vector database, storage for next generation AI applications
NeMo-Guardrails
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
qdrant
Qdrant - Vector Database for the next generation of AI applications. Also available in the cloud https://cloud.qdrant.io/
trino
Official repository of Trino, the distributed SQL query engine for big data, formerly known as PrestoSQL (https://trino.io)
trulens
Evaluation and Tracking for LLM Experiments
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
weaviate
Weaviate is an open source vector database that stores both objects and vectors, allowing for combining vector search with structured filtering with the fault-tolerance and scalability of a cloud-native database, all accessible through GraphQL, REST, and various language clients.