facebookresearch / memoryLinks
Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsely activated memory layers complement compute-heavy dense feed-forward layers, providing dedicated capacity to store and retrieve information cheaply.
☆370Updated last year
Alternatives and similar repositories for memory
Users that are interested in memory are comparing it to the libraries listed below
Sorting:
- Tina: Tiny Reasoning Models via LoRA☆313Updated 4 months ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆621Updated 3 weeks ago
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆355Updated last week
- [ICML 2024] CLLMs: Consistency Large Language Models☆411Updated last year
- A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).☆344Updated last month
- A project to improve skills of large language models☆786Updated last week
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆251Updated last year
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆227Updated 2 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆469Updated 8 months ago
- ☆206Updated last year
- ☆230Updated 2 months ago
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆140Updated 5 months ago
- Normalized Transformer (nGPT)☆197Updated last year
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆175Updated last year
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆276Updated 3 months ago
- Simple & Scalable Pretraining for Neural Architecture Research☆307Updated last month
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆182Updated 7 months ago
- Pretraining and inference code for a large-scale depth-recurrent language model☆859Updated last month
- PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention…☆294Updated last year
- A family of compressed models obtained via pruning and knowledge distillation☆364Updated 2 months ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆201Updated last year
- [NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models☆236Updated 3 months ago
- Exploring Applications of GRPO☆251Updated 5 months ago
- A simplified implementation for experimenting with RLVR on GSM8K, This repository provides a starting point for exploring reasoning.☆158Updated 11 months ago
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆358Updated 7 months ago
- PyTorch implementation of models from the Zamba2 series.☆186Updated last year
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)☆163Updated 9 months ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆235Updated 6 months ago
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆343Updated 2 months ago
- Reproducible, flexible LLM evaluations☆331Updated this week