OpenMOSS/CoLLiE

Collaborative Training of Large Language Models in an Efficient Way

/ 100

Emerging

CoLLiE helps machine learning engineers and researchers efficiently train large language models from scratch or fine-tune existing ones. You provide your data and a base model (like MOSS or LLaMA), and it outputs a highly optimized, trained large language model. It's designed for professionals working with state-of-the-art language AI.

419 stars. No commits in the last 6 months.

Use this if you need to build or adapt large language models for specific tasks but want to minimize training time, memory usage, and computational costs.

Not ideal if you're a casual user looking for a no-code solution or don't have experience with deep learning frameworks like PyTorch and distributed training setups.

large-language-models model-training deep-learning AI-research natural-language-processing

Stale 6m No Package No Dependents

Maintenance 0 / 25

Adoption 10 / 25

Maturity 16 / 25

Community 19 / 25

How are scores calculated?

Stars

419

Forks

Language

Python

License

Apache-2.0

Related models

kossisoroyce/timber

Ollama for classical ML models. AOT compiler that turns XGBoost, LightGBM, scikit-learn,...

zamfir70/TransXform

Training supervisor — live monitoring, early stopping, and checkpoint management for LLM fine-tuning

Explore Transformer Models

All categories Trending Transformer directory Insights