mebubo

mebubo's Stars

• vllm-project/vllm

  A high-throughput and memory-efficient inference and serving engine for LLMs

  Language:Python30.9k2515.4k4.7k

• lucidrains/vit-pytorch

  Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

  Language:Python20.8k1542683.1k

• huggingface/candle

  Minimalist ML framework for Rust

  Language:Rust15.9k156723964

• rougier/numpy-100

  100 numpy exercises (with solutions)

  Language:Python12.2k204895.8k

• stas00/ml-engineering

  Machine Learning Engineering Open Book

  Language:Python11.8k11730717

• OpenAccess-AI-Collective/axolotl

  Go ahead and axolotl questions

  Language:Python6.9k50597750

• ml-explore/mlx-examples

  Examples in the MLX framework

  Language:Python6.3k71514896

• pytorch-labs/gpt-fast

  Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

  Language:Python5.7k60104514

• bbycroft/llm-viz

  3D Visualization of an GPT-style LLM

  Language:TypeScript4.1k3314449

• danielgross/localpilot

  Language:Python3.4k2626143

• webrtc-for-the-curious/webrtc-for-the-curious

  WebRTC for the Curious: Go beyond the APIs

  Language:Python2k6363196

• jacobhilton/deep_learning_curriculum

  Language model alignment-focused deep learning curriculum

  1.3k171110

• JShollaj/awesome-llm-interpretability

  A curated list of Large Language Model (LLM) Interpretability resources.

  1.2k19294

• neelnanda-io/TransformerLens

  A library for mechanistic interpretability of GPT-style language models

  Language:Python92013192205

• facundoolano/feedi

  RSS + Mastodon feed reader

  Language:Python89392428

• AlignmentResearch/tuned-lens

  Tools for understanding how transformer predictions are built layer-by-layer

  Language:Python43875447

• collin-burns/discovering_latent_knowledge

  Language:Python2526236

• modal-labs/turbo-art

  A playground for creative exploration that uses SDXL Turbo.

  Language:Svelte2145520

• ai-safety-foundation/sparse_autoencoder

  Sparse Autoencoder for Mechanistic Interpretability

  Language:Python19144139

• HoagyC/sparse_coding

  Using sparse coding to find distributed representations used by neural networks.

  Language:Jupyter Notebook1902329

• HazyResearch/zoology

  Understand and test language model architectures on synthetic tasks.

  Language:Python163142128

• virchau13/automatic1111-webui-nix

  AUTOMATIC1111/stable-diffusion-webui for CUDA and ROCm on NixOS

  Language:Nix1559722

• alan-cooney/CircuitsVis

  Mechanistic Interpretability Visualizations using React

  Language:Jupyter Notebook15032524

• AllenDowney/ProbablyOverthinkingIt

  Supplementary material for my book, Probably Overthinking It.

  Language:Jupyter Notebook14314249

• neelnanda-io/1L-Sparse-Autoencoder

  Language:Python1092111

• google-deepmind/debate

  Formalizing stochastic doubly-efficient debate

  Language:Lean939017

• alan-cooney/transformer-from-scratch

  Decoder only transformer, built from scratch with PyTorch

  Language:Python25306

• jamescampbell57/llama-lying

  Language:Jupyter Notebook102

• thestephencasper/mechanistic_interpretability_challenge

  8211

• danwilhelm/cumsum_transformer

  Language:Jupyter Notebook10