Alternatives and similar repositories for modalities

Users that are interested in modalities are comparing it to the libraries listed below

• VectorInstitute / vector-inference
  Efficient LLM inference on Slurm clusters using vLLM.
  ☆69Updated last week
• epfml / llm-baselines
  nanoGPT-like codebase for LLM training
  ☆102Updated 2 months ago
• pietrobarbiero / pytorch_explain
  PyTorch Explain: Interpretable Deep Learning in Python.
  ☆159Updated last year
• srush / do-we-need-attention
  ☆166Updated 2 years ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆128Updated 2 years ago
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆63Updated last year
• microsoft / mutransformers
  some common Huggingface transformers in maximal update parametrization (µP)
  ☆82Updated 3 years ago
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆221Updated 3 weeks ago
• tommasomncttn / mergenetic
  Flexible library for merging large language models (LLMs) via evolutionary optimization (ACL 2025 Demo).
  ☆80Updated 2 weeks ago
• princeton-nlp / TransformerPrograms
  [NeurIPS 2023] Learning Transformer Programs
  ☆162Updated last year
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆123Updated 7 months ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆149Updated last month
• ml-jku / SDLG
  SDLG is an efficient method to accurately estimate aleatoric semantic uncertainty in LLMs
  ☆25Updated last year
• mechanistic-interpretability-grokking / progress-measures-paper
  ☆68Updated 2 years ago
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆81Updated 9 months ago
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆186Updated 2 years ago
• luyug / magix
  Supercharge huggingface transformers with model parallelism.
  ☆77Updated 2 weeks ago
• google-deepmind / mishax
  ☆136Updated 4 months ago
• bartbussmann / BatchTopK
  Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)
  ☆44Updated 2 weeks ago
• Sea-Snell / grokking
  unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
  ☆78Updated 3 years ago
• UW-Madison-Lee-Lab / LanguageInterfacedFineTuning
  Code for Language-Interfaced FineTuning for Non-Language Machine Learning Tasks.
  ☆129Updated 8 months ago
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆59Updated last year
• AntreasAntoniou / kubejobs
  ☆31Updated 3 months ago
• srush / mamba-primer
  ☆37Updated last year
• ARBORproject / arborproject.github.io
  ☆81Updated 5 months ago
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆28Updated last month
• msakarvadia / AttentionLens
  Interpretating the latent space representations of attention head outputs for LLMs
  ☆34Updated 11 months ago
• EleutherAI / concept-erasure
  Erasing concepts from neural representations with provable guarantees
  ☆232Updated 6 months ago
• wesg52 / universal-neurons
  Universal Neurons in GPT2 Language Models
  ☆30Updated last year
• guy-dar / embedding-space
  ☆54Updated 2 years ago