facebookresearch / MemoryMosaicsLinks
Memory Mosaics are networks of associative memories working in concert to achieve a prediction task.
☆48Updated 7 months ago
Alternatives and similar repositories for MemoryMosaics
Users that are interested in MemoryMosaics are comparing it to the libraries listed below
Sorting:
- ☆85Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆83Updated 10 months ago
- ☆53Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆78Updated 9 months ago
- One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation☆42Updated 11 months ago
- ☆28Updated 7 months ago
- ☆34Updated 8 months ago
- Universal Neurons in GPT2 Language Models☆30Updated last year
- ☆104Updated 11 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆38Updated 3 months ago
- ☆45Updated last year
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆92Updated 10 months ago
- nanoGPT-like codebase for LLM training☆107Updated 4 months ago
- The repository contains code for Adaptive Data Optimization☆25Updated 9 months ago
- Official Pytorch Implementation of "The Curse of Depth in Large Language Models" by Wenfang Sun, Xinyuan Song, Pengxiang Li, Lu Yin,Yefen…☆56Updated last month
- ☆55Updated last year
- ☆46Updated last year
- Language models scale reliably with over-training and on downstream tasks☆99Updated last year
- Sparse and discrete interpretability tool for neural networks☆63Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆162Updated 2 months ago
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- ☆69Updated last year
- Official PyTorch Implementation of the Longhorn Deep State Space Model☆53Updated 9 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆129Updated 9 months ago
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆81Updated 2 years ago
- ☆39Updated 2 weeks ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆192Updated last year
- EvaByte: Efficient Byte-level Language Models at Scale☆109Updated 5 months ago
- Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Mode…☆116Updated last year
- ☆34Updated last year