-
Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence
Paper • 2404.05892 • Published • 28 -
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Paper • 2312.00752 • Published • 131 -
RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
Paper • 2404.07839 • Published • 36 -
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
Paper • 2404.07143 • Published • 92
Collections
Discover the best community collections!
Collections including paper arxiv:2404.08801
-
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Paper • 2404.08801 • Published • 61 -
Ring Attention with Blockwise Transformers for Near-Infinite Context
Paper • 2310.01889 • Published • 8 -
World Model on Million-Length Video And Language With RingAttention
Paper • 2402.08268 • Published • 33 -
Scaling Transformer to 1M tokens and beyond with RMT
Paper • 2304.11062 • Published • 2
-
OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework
Paper • 2404.14619 • Published • 120 -
Multi-Head Mixture-of-Experts
Paper • 2404.15045 • Published • 53 -
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Paper • 2404.14219 • Published • 229 -
Learn Your Reference Model for Real Good Alignment
Paper • 2404.09656 • Published • 79
-
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Paper • 2404.08801 • Published • 61 -
TransformerFAM: Feedback attention is working memory
Paper • 2404.09173 • Published • 42 -
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
Paper • 2404.07143 • Published • 92
-
PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
Paper • 2309.10400 • Published • 22 -
winglian/Llama-3-8b-64k-PoSE
Text Generation • Updated • 3.82k • 67 -
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Paper • 2404.08801 • Published • 61
-
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Paper • 2404.08801 • Published • 61 -
RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
Paper • 2404.07839 • Published • 36 -
Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence
Paper • 2404.05892 • Published • 28 -
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Paper • 2312.00752 • Published • 131
-
Rho-1: Not All Tokens Are What You Need
Paper • 2404.07965 • Published • 79 -
VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time
Paper • 2404.10667 • Published • 12 -
Instruction-tuned Language Models are Better Knowledge Learners
Paper • 2402.12847 • Published • 25 -
DoRA: Weight-Decomposed Low-Rank Adaptation
Paper • 2402.09353 • Published • 18
-
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 565 -
BitNet: Scaling 1-bit Transformers for Large Language Models
Paper • 2310.11453 • Published • 94 -
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Paper • 2404.02258 • Published • 99 -
TransformerFAM: Feedback attention is working memory
Paper • 2404.09173 • Published • 42
-
TransformerFAM: Feedback attention is working memory
Paper • 2404.09173 • Published • 42 -
Ring Attention with Blockwise Transformers for Near-Infinite Context
Paper • 2310.01889 • Published • 8 -
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Paper • 2404.08801 • Published • 61