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.
☆344Updated 8 months ago
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☆275Updated last week
- Decentralized RL Training at Scale☆441Updated this week
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆327Updated 3 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆244Updated 6 months ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆433Updated last week
- A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).☆272Updated this week
- ☆211Updated 6 months ago
- PyTorch building blocks for the OLMo ecosystem☆274Updated this week
- ☆193Updated 8 months ago
- An extension of the nanoGPT repository for training small MOE models.☆178Updated 5 months ago
- [ICML 2024] CLLMs: Consistency Large Language Models☆400Updated 9 months ago
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆240Updated last year
- Scalable toolkit for efficient model reinforcement☆626Updated this week
- A project to improve skills of large language models☆529Updated this week
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆173Updated 7 months ago
- Simple & Scalable Pretraining for Neural Architecture Research☆287Updated 2 weeks ago
- Normalized Transformer (nGPT)☆186Updated 9 months ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆199Updated last year
- PyTorch implementation of models from the Zamba2 series.☆184Updated 7 months ago
- PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention…☆291Updated last year
- Code for the paper: "Learning to Reason without External Rewards"☆345Updated last month
- A simplified implementation for experimenting with RLVR on GSM8K, This repository provides a starting point for exploring reasoning.☆121Updated 6 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆429Updated 3 months ago
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆220Updated last month
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆179Updated 2 months ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆228Updated last month
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆324Updated 9 months ago
- ☆514Updated 3 weeks ago
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆120Updated last week
- [NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models☆226Updated 3 months ago