Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Ongoing research training transformer models at scale

Models, data loaders and abstractions for language processing, powered by PyTorch

🤗 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.

🐟🐟🐟 机器学习面试复习资源

Performance analysis of predictive (alpha) stock factors