Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up

Collections

Discover the best community collections!

Collections including paper arxiv:2501.06425

CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data

Paper • 2404.15653 • Published Apr 24, 2024 • 28
MoDE: CLIP Data Experts via Clustering

Paper • 2404.16030 • Published Apr 24, 2024 • 14
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning

Paper • 2405.12130 • Published May 20, 2024 • 50
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Paper • 2405.12981 • Published May 21, 2024 • 32

LM Architectures

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

Paper • 2404.08801 • Published Apr 12, 2024 • 67
RecurrentGemma: Moving Past Transformers for Efficient Open Language Models

Paper • 2404.07839 • Published Apr 11, 2024 • 46
Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence

Paper • 2404.05892 • Published Apr 8, 2024 • 36
Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Paper • 2312.00752 • Published Dec 1, 2023 • 143

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 610
BitNet: Scaling 1-bit Transformers for Large Language Models

Paper • 2310.11453 • Published Oct 17, 2023 • 97
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Paper • 2404.02258 • Published Apr 2, 2024 • 104
TransformerFAM: Feedback attention is working memory

Paper • 2404.09173 • Published Apr 14, 2024 • 43

Previous
1
2
3
Next

Company

TOS Privacy About Jobs

Website

Models Datasets Spaces Pricing Docs