#61 · Primary category： Foundation Models
MiniMax-01
The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention
Project last updated：07/07/25
GitHub Stars
3.5K
Forks
332
Contributors
6
License
MIT
Why we included this project
MiniMax-01 pairs a text model with a vision-language counterpart, and both share an unusual design decision: linear attention rather than the full-attention transformer most large models rely on. That choice is what lets the text model hold a million tokens of context while keeping training and inference costs below what a comparably sized dense model would demand. Teams dealing with long documents, agent workflows that need broad conversation memory, or multimodal inputs that also run long will find the released weights, training details, and benchmark results worth studying. Just size your hardware before planning local deployment: at 456 billion parameters with only a fraction active per token, this is not a laptop-friendly model.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
MiniCPM-V
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
generative-models
Generative Models by Stability AI
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities