apple / ml-actLinks
☆53Updated 8 months ago
Alternatives and similar repositories for ml-act
Users that are interested in ml-act are comparing it to the libraries listed below
Sorting:
- WIP☆94Updated 11 months ago
- Sparse Autoencoders for Stable Diffusion XL models.☆69Updated 2 weeks ago
- [ICML 2025] Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction☆56Updated 2 months ago
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆84Updated last year
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆55Updated 4 months ago
- supporting pytorch FSDP for optimizers☆84Updated 8 months ago
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆292Updated 2 weeks ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆190Updated last year
- DeMo: Decoupled Momentum Optimization☆190Updated 8 months ago
- PyTorch library for Active Fine-Tuning☆87Updated 5 months ago
- Synthetic Alphabet Dataset☆19Updated 4 months ago
- This is the official repository for the paper "Flora: Low-Rank Adapters Are Secretly Gradient Compressors" in ICML 2024.☆104Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆130Updated last year
- Focused on fast experimentation and simplicity☆76Updated 7 months ago
- ☆34Updated 10 months ago
- $100K or 100 Days: Trade-offs when Pre-Training with Academic Resources☆143Updated 2 months ago
- These papers will provide unique insightful concepts that will broaden your perspective on neural networks and deep learning☆48Updated last year
- Minimal (truly) muP implementation, consistent with TP4 and TP5 papers notation☆14Updated 2 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆149Updated last month
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆178Updated last month
- A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.☆174Updated last month
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆127Updated 11 months ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- Official implementation of MAIA, A Multimodal Automated Interpretability Agent☆83Updated last month
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 8 months ago
- ☆83Updated 11 months ago
- ☆17Updated 8 months ago
- ☆30Updated 8 months ago
- ☆136Updated 4 months ago
- ☆31Updated last year