DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models
Paper
•
2309.14509
•
Published
•
18
Research
-
-
LLM Augmented LLMs: Expanding Capabilities through Composition
Paper • 2401.02412 • Published • 38 -
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Paper • 2401.06066 • Published • 53 -
Tuning Language Models by Proxy
Paper • 2401.08565 • Published • 23 -
Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding
Paper • 2401.12954 • Published • 31 -
ReFT: Reasoning with Reinforced Fine-Tuning
Paper • 2401.08967 • Published • 30 -
MambaByte: Token-free Selective State Space Model
Paper • 2401.13660 • Published • 57 -
RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Paper • 2401.18059 • Published • 42 -
Specialized Language Models with Cheap Inference from Limited Domain Data
Paper • 2402.01093 • Published • 47 -
Repeat After Me: Transformers are Better than State Space Models at Copying
Paper • 2402.01032 • Published • 24 -
OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models
Paper • 2402.01739 • Published • 27 -
Scaling Laws for Downstream Task Performance of Large Language Models
Paper • 2402.04177 • Published • 18 -
An Interactive Agent Foundation Model
Paper • 2402.05929 • Published • 29 -
BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
Paper • 2402.04291 • Published • 50 -
Mixtures of Experts Unlock Parameter Scaling for Deep RL
Paper • 2402.08609 • Published • 36 -
Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model
Paper • 2402.07827 • Published • 47 -
Tandem Transformers for Inference Efficient LLMs
Paper • 2402.08644 • Published • 10 -
Learning to Learn Faster from Human Feedback with Language Model Predictive Control
Paper • 2402.11450 • Published • 22 -
DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows
Paper • 2402.10379 • Published • 31 -
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
Paper • 2402.13753 • Published • 115 -
User-LLM: Efficient LLM Contextualization with User Embeddings
Paper • 2402.13598 • Published • 20 -
OmniPred: Language Models as Universal Regressors
Paper • 2402.14547 • Published • 13 -
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
Paper • 2402.14083 • Published • 48 -
MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs
Paper • 2402.15627 • Published • 38 -
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 611 -
Stop Regressing: Training Value Functions via Classification for Scalable Deep RL
Paper • 2403.03950 • Published • 16 -
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Paper • 2403.03507 • Published • 188 -
Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
Paper • 2403.07816 • Published • 41 -
Chronos: Learning the Language of Time Series
Paper • 2403.07815 • Published • 47 -
Adding NVMe SSDs to Enable and Accelerate 100B Model Fine-tuning on a Single GPU
Paper • 2403.06504 • Published • 53 -
PERL: Parameter Efficient Reinforcement Learning from Human Feedback
Paper • 2403.10704 • Published • 59 -
TnT-LLM: Text Mining at Scale with Large Language Models
Paper • 2403.12173 • Published • 20 -
RLHF Workflow: From Reward Modeling to Online RLHF
Paper • 2405.07863 • Published • 70 -
SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization
Paper • 2405.11582 • Published • 17 -
Towards Modular LLMs by Building and Reusing a Library of LoRAs
Paper • 2405.11157 • Published • 30 -
Block Transformer: Global-to-Local Language Modeling for Fast Inference
Paper • 2406.02657 • Published • 40 -
GEB-1.3B: Open Lightweight Large Language Model
Paper • 2406.09900 • Published • 21 -
Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP
Paper • 2407.00402 • Published • 23 -
Agentless: Demystifying LLM-based Software Engineering Agents
Paper • 2407.01489 • Published • 62 -
On Leakage of Code Generation Evaluation Datasets
Paper • 2407.07565 • Published • 6 -
SpreadsheetLLM: Encoding Spreadsheets for Large Language Models
Paper • 2407.09025 • Published • 136 -
E5-V: Universal Embeddings with Multimodal Large Language Models
Paper • 2407.12580 • Published • 40 -
Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning
Paper • 2408.00690 • Published • 25 -
CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases
Paper • 2408.03910 • Published • 18 -
Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers
Paper • 2408.06195 • Published • 71 -
OLMoE: Open Mixture-of-Experts Language Models
Paper • 2409.02060 • Published • 79 -
Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts
Paper • 2409.16040 • Published • 14 -
Large Language Models as Markov Chains
Paper • 2410.02724 • Published • 32 -
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
Paper • 2410.08815 • Published • 49 -
Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free
Paper • 2410.10814 • Published • 51 -
HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems
Paper • 2411.02959 • Published • 69 -
Star Attention: Efficient LLM Inference over Long Sequences
Paper • 2411.17116 • Published • 54 -
Personalized Graph-Based Retrieval for Large Language Models
Paper • 2501.02157 • Published • 31 -
SRMT: Shared Memory for Multi-agent Lifelong Pathfinding
Paper • 2501.13200 • Published • 67 -
Scaling Embedding Layers in Language Models
Paper • 2502.01637 • Published • 24 -
A Comprehensive Survey on Long Context Language Modeling
Paper • 2503.17407 • Published • 43