LFM and LFM2

LFM2 is an improved successor implementation that supersedes the original LFM, with both tools providing PyTorch implementations of Liquid AI's foundation models but LFM2 representing the newer, optimized version of the architecture.

LFM
56
Established
LFM2
55
Established
Maintenance 10/25
Adoption 10/25
Maturity 16/25
Community 20/25
Maintenance 10/25
Adoption 6/25
Maturity 24/25
Community 15/25
Stars: 207
Forks: 36
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 23
Forks: 5
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No risk flags

About LFM

kyegomez/LFM

An open source implementation of LFMs from Liquid AI: Liquid Foundation Models

This project offers an experimental, open-source version of Liquid Foundation Models, which are advanced neural networks designed for adaptive processing. It takes in structured data, such as sequences of numerical embeddings representing text or other complex information, and produces processed sequences that can be used for further analysis or predictions. Researchers and machine learning practitioners exploring novel neural architectures for complex data tasks would use this.

neural-networks sequence-modeling adaptive-learning machine-learning-research artificial-intelligence

About LFM2

kyegomez/LFM2

A simple and minimal open source implementation of "Introducing LFM2: The Fastest On-Device Foundation Models on the Market" from Liquid AI in Pytorch

This project provides a foundational building block for artificial intelligence models, specifically designed for researchers and developers working on language-based AI. It takes in numerical representations of text (token IDs) and processes them to produce logical outputs, often used for tasks like text generation or understanding. Anyone experimenting with or building new language models would find this useful.

AI-model-development natural-language-processing generative-AI-research machine-learning-engineering

Scores updated daily from GitHub, PyPI, and npm data. How scores work