oushu1zhangxiangxuan1's Stars
mli/autocut
用文本编辑器剪视频
chidiwilliams/buzz
Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
lloyd/yajl
A fast streaming JSON parsing library in C.
ICRAR/ijson
Iterative JSON parser with Pythonic interfaces
XGenerationLab/M-Schema
a semi-structure representation of database schema
XGenerationLab/XiYan-SQL
A MULTI-GENERATOR ENSEMBLE FRAMEWORK FOR NATURAL LANGUAGE TO SQL
HasanAlpCaferoglu/E-SQL
ljinkai/weekly
独立开发产品变现周刊,每周五发布。
ShayanTalaei/CHESS
Contextual Harnessing for Efficient SQL Synthesis
google/BIG-bench
Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models
daerduoCarey/where2act
Where2Act: From Pixels to Actions for Articulated 3D Objects
OpenGVLab/LLaMA-Adapter
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
clorislili/ManipLLM
The official codebase for ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation(cvpr 2024)
allenai/ai2thor
An open-source platform for Visual AI.
microsoft/LLaVA-Med
Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.
haotian-liu/LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
infiniflow/ragflow
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
tobymao/sqlglot
Python SQL Parser and Transpiler
state-spaces/mamba
Mamba SSM architecture
facebookresearch/xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.
Project-HAMi/HAMi
Heterogeneous AI Computing Virtualization Middleware
gpues/4paradigm-k8s-vgpu-scheduler
OpenAIOS vGPU scheduler for Kubernetes is originated from the OpenAIOS project to virtualize GPU device memory.
4paradigm/k8s-vgpu-scheduler
OpenAIOS vGPU device plugin for Kubernetes is originated from the OpenAIOS project to virtualize GPU device memory, in order to allow applications to access larger memory space than its physical capacity. It is designed for ease of use of extended device memory for AI workloads.
grgalex/nvshare
Practical GPU Sharing Without Memory Size Constraints
artidoro/qlora
QLoRA: Efficient Finetuning of Quantized LLMs
deepseek-ai/DeepSeek-MoE
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
tiangolo/pydantic-sqlalchemy
Tools to convert SQLAlchemy models to Pydantic models
fastapi/sqlmodel
SQL databases in Python, designed for simplicity, compatibility, and robustness.
yizhongw/self-instruct
Aligning pretrained language models with instruction data generated by themselves.
FasterDecoding/Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads