MrQianJinSi's Stars
supabase/supabase
The open source Firebase alternative. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.
microsoft/graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
chenran-li/RQL-release
(NeurIPS 2023) Residual Q-Learning: Offline and Online Policy Customization without Value
liguodongiot/llm-action
本项目旨在分享大模型相关技术原理以及实战经验。
sgl-project/sglang
SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.
microsoft/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
skypilot-org/skypilot
SkyPilot: Run LLMs, AI, and Batch jobs on any cloud. Get maximum savings, highest GPU availability, and managed execution—all with a simple interface.
cybertronai/gradient-checkpointing
Make huge neural nets fit in memory
Computer-Vision-in-the-Wild/CVinW_Readings
A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''
OpenDevin/OpenDevin
🐚 OpenDevin: Code Less, Make More
OpenGVLab/InternVL
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4V. 接近GPT-4V表现的可商用开源多模态对话模型
haotian-liu/LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
ShareGPT4Omni/ShareGPT4V
[ECCV 2024] ShareGPT4V: Improving Large Multi-modal Models with Better Captions
BradyFU/Awesome-Multimodal-Large-Language-Models
:sparkles::sparkles:Latest Advances on Multimodal Large Language Models
LambdaLabsML/examples
Deep Learning Examples
deepseek-ai/DeepSeek-Coder-V2
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
mli/paper-reading
深度学习经典、新论文逐段精读
iree-org/iree
A retargetable MLIR-based machine learning compiler and runtime toolkit.
eric-mitchell/direct-preference-optimization
Reference implementation for DPO (Direct Preference Optimization)
Bharath2/iLQR
iterative Linear Quadratic Regulator with constraints.
FlagOpen/FlagAttention
A collection of memory efficient attention operators implemented in the Triton language.
FlagOpen/FlagGems
FlagGems is an operator library for large language models implemented in Triton Language.
TimDettmers/bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
huggingface/trl
Train transformer language models with reinforcement learning.
srush/Triton-Puzzles
Puzzles for learning Triton
allwefantasy/byzer-llm
Easy, fast, and cheap pretrain,finetune, serving for everyone
labmlai/annotated_deep_learning_paper_implementations
🧑🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
aladdinpersson/Machine-Learning-Collection
A resource for learning about Machine learning & Deep Learning
karpathy/llm.c
LLM training in simple, raw C/CUDA
adam-maj/deep-learning
A deep-dive on the entire history of deep-learning