EvolvingLMMs-Lab/lmms-engine
A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.
This engine helps machine learning engineers and researchers train powerful multimodal AI models efficiently. You input datasets containing various data types like images, audio, and text, and it outputs a highly optimized, ready-to-use AI model. It's designed for those who build and fine-tune advanced AI systems that can understand and generate multiple forms of content.
740 stars. Actively maintained with 8 commits in the last 30 days.
Use this if you are a machine learning engineer or researcher focused on developing and scaling state-of-the-art multimodal AI models that combine visual, auditory, and textual data.
Not ideal if you are looking for a plug-and-play solution without deep involvement in model architecture, training pipelines, or distributed systems.
Stars
740
Forks
32
Language
Python
License
—
Category
Last pushed
Mar 12, 2026
Commits (30d)
8
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/EvolvingLMMs-Lab/lmms-engine"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aalok-sathe/surprisal
A unified interface for computing surprisal (log probabilities) from language models! Supports...
reasoning-machines/pal
PaL: Program-Aided Language Models (ICML 2023)
FunnySaltyFish/Better-Ruozhiba
【逐条处理完成】人为审核+修改每一条的弱智吧精选问题QA数据集
microsoft/monitors4codegen
Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static...
FreedomIntelligence/EchoX
EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs