sunkaianna

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.

Auto-GPT

An experimental open-source attempt to make GPT-4 fully autonomous.

BiLLP

ChatGLM-6B

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

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

CRATE

Code for CRATE (Coding RAte reduction TransformEr).

Cream

This is a collection of our NAS and Vision Transformer work.

cuvs

cuVS - a library for vector search and clustering on the GPU

diffmimic

[ICLR 2023] DiffMimic: Efficient Motion Mimicking with Differentiable Physics https://arxiv.org/abs/2304.03274

dinov2

PyTorch code and models for the DINOv2 self-supervised learning method.

enchanted

Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.

FastChat

An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5.

FastSAM

Fast Segment Anything

FireAct

FireAct: Toward Language Agent Fine-tuning

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

llama2.c

Inference Llama 2 in one file of pure C

llama_index

LlamaIndex (formerly GPT Index) is a data framework for your LLM applications

llm-viz

3D Visualization of an GPT-style LLM

MiniCPM-V

MiniCPM-V 2.0: An Efficient End-side MLLM with Strong OCR and Understanding Capabilities

mlc-MiniCPM

MiniCPM on Android platform.

MobileSAM

This is the offiicial code for MobileSAM project that makes Segment Anything Model lightweight and faster

pytorch-forecasting

Time series forecasting with PyTorch

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.

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

SchurVINS

swift

ms-swift: Use PEFT or Full-parameter to finetune 200+ LLMs or 15+ MLLMs

UniChart

Vary-tiny-600k

Vary-tiny codebase upon LAVIS （for training from scratch）and a PDF image-text pairs data (about 600k including English/Chinese)

VisualGLM-6B

Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型