Kai Sun's repositories
raft
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
cuvs
cuVS - a library for vector search and clustering on the GPU
InternVL
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4V. 接近GPT-4V表现的可商用开源模型
ragflow
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
pytorch-forecasting
Time series forecasting with PyTorch
swift
ms-swift: Use PEFT or Full-parameter to finetune 200+ LLMs or 15+ MLLMs
MiniCPM-V
MiniCPM-V 2.0: An Efficient End-side MLLM with Strong OCR and Understanding Capabilities
Vary-tiny-600k
Vary-tiny codebase upon LAVIS (for training from scratch)and a PDF image-text pairs data (about 600k including English/Chinese)
enchanted
Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.
mlc-MiniCPM
MiniCPM on Android platform.
AdvancedLiterateMachinery
A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Alibaba DAMO Academy.
llama_index
LlamaIndex (formerly GPT Index) is a data framework for your LLM applications
llm-viz
3D Visualization of an GPT-style LLM
FireAct
FireAct: Toward Language Agent Fine-tuning
CRATE
Code for CRATE (Coding RAte reduction TransformEr).
llama2.c
Inference Llama 2 in one file of pure C
dinov2
PyTorch code and models for the DINOv2 self-supervised learning method.
MobileSAM
This is the offiicial code for MobileSAM project that makes Segment Anything Model lightweight and faster
Cream
This is a collection of our NAS and Vision Transformer work.
FastSAM
Fast Segment Anything
VisualGLM-6B
Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型
ChatGLM-6B
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
FastChat
An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5.
diffmimic
[ICLR 2023] DiffMimic: Efficient Motion Mimicking with Differentiable Physics https://arxiv.org/abs/2304.03274
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地部署 (Chinese LLaMA & Alpaca LLMs)
ColossalAI
Making large AI models cheaper, faster and more accessible