#54 · Primary category： Foundation Models
CPM-Live
Live Training for Open-source Big Models
Project last updated：07/07/26
GitHub Stars
501
Forks
40
Contributors
7
License
Other
Why we included this project
CPM-Live is a running record of how the CPM bilingual models were actually trained. Rather than a clean post-hoc release, you get the training plan and daily logs as the runs were happening, plus checkpoints you could download at each stage, from CPM-Ant and CPM-Ant+ through the 10-billion-parameter CPM-Bee. That structure exposes the real decisions about pretraining data, architecture, and scaling behind the final weights, not just the trained parameters. The CPM-Bee base model is fine-tunable and commercially usable, and it handles text completion, translation, question answering, and summarization in both Chinese and English. Teams building Chinese-facing NLP applications or comparing open bilingual backbones will find both the released models and their documented recipes directly usable.
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