snimu

snimu's Stars

• GistNoesis/FourierKAN

  Language:Python71559

• alasdairforsythe/tokenmonster

  Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript

  Language:Go56220

• VainF/Torch-Pruning

  [CVPR 2023] DepGraph: Towards Any Structural Pruning

  Language:Python2.8k340

• FoundationVision/VAR

  [NeurIPS 2024 Best Paper][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

  Language:Jupyter Notebook6.4k447

• haizelabs/dspy-redteam

  Red-Teaming Language Models with DSPy

  Language:Python15319

• custom-build-robots/ai-agents-with-CrewAI

  This program uses CrewAI to build a web-app using three agents doing some research stuff in the internet.

  Language:Python6228

• epfml/llm-baselines

  nanoGPT-like codebase for LLM training

  Language:Python8325

• jafioti/luminal

  Deep learning at the speed of light.

  Language:Rust1.5k89

• huggingface/llm-swarm

  Manage scalable open LLM inference endpoints in Slurm clusters

  Language:Python24724

• center-for-humans-and-machines/transformer-heads

  Toolkit for attaching, training, saving and loading of new heads for transformer models

  Language:Jupyter Notebook25923

• zjunlp/EasyEdit

  [ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

  Language:Jupyter Notebook2k245

• roboflow/supervision

  We write your reusable computer vision tools. 💜

  Language:Python24.6k1.8k

• stanfordnlp/dspy

  DSPy: The framework for programming—not prompting—language models

  Language:Python21k1.6k

• astral-sh/uv

  An extremely fast Python package and project manager, written in Rust.

  Language:Rust36k973

• apple/ml-mgie

  Language:Python3.9k253

• BradyFU/Awesome-Multimodal-Large-Language-Models

  :sparkles::sparkles:Latest Advances on Multimodal Large Language Models

  13.5k861

• AnswerDotAI/RAGatouille

  Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

  Language:Python3.2k215

• lucidrains/rotary-embedding-torch

  Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch

  Language:Python60947

• jgraph/drawio-desktop

  Official electron build of draw.io

  Language:JavaScript52k5.1k

• eliphatfs/calibur

  Conversion between different conventions of camera matrices and transform matrices.

  Language:Python982

• google-deepmind/ferminet

  An implementation of the Fermionic Neural Network for ab-initio electronic structure calculations

  Language:Python746134

• johnmarktaylor91/torchlens

  Package for extracting and mapping the results of every single tensor operation in a PyTorch model in one line of code.

  Language:Python53519

• lucaswadedavis/funkyllama-7b-chat

  Language:Python51

• openai/openai-cookbook

  Examples and guides for using the OpenAI API

  Language:MDX61.2k9.8k

• MrNeRF/gaussian-splatting-cuda

  3D Gaussian Splatting, reimagined: Unleashing unmatched speed with C++ and CUDA from the ground up!

  Language:C95276

• drivendataorg/erdantic

  Entity relationship diagrams for Python data model classes like Pydantic

  Language:Python35323

• EleutherAI/elk

  Keeping language models honest by directly eliciting knowledge encoded in their activations.

  Language:Python19233

• EleutherAI/pythia

  The hub for EleutherAI's work on interpretability and learning dynamics

  Language:Jupyter Notebook2.3k175

• microsoft/LoRA

  Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

  Language:Python11.1k701

• Dao-AILab/flash-attention

  Fast and memory-efficient exact attention

  Language:Python15.1k1.4k