RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
akhaliq
Abstract
We introduce RecurrentGemma, an open language model which uses Google's novel Griffin architecture. Griffin combines linear recurrences with local attention to achieve excellent performance on language. It has a fixed-sized state, which reduces memory use and enables efficient inference on long sequences. We provide a pre-trained model with 2B non-embedding parameters, and an instruction tuned variant. Both models achieve comparable performance to Gemma-2B despite being trained on fewer tokens.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models (2024)
- Long-Context Language Modeling with Parallel Context Encoding (2024)
- Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention (2024)
- Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference (2024)
- Cross-Architecture Transfer Learning for Linear-Cost Inference Transformers (2024)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Nice job!
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper