CodeGeeX is a large-scale multilingual code generation model with 13 billion parameters, pre-trained on a large code corpus of more than 20 programming languages. CodeGeeX supports 15+ programming languages for both code generation and translation
THUDM/CodeGeeX is a Hugging Face model space containing pre-trained models and code snippets for natural language processing tasks, specifically focused on text generation and language translation. The models in this space are based on deep learning architectures and can be fine-tuned on specific tasks. The CodeGeeX models are optimized for performance and efficiency, making them suitable for deployment in production systems. The pre-trained models can generate coherent text in various languages and styles, and also support translation between multiple languages. This model space also includes a range of code snippets for text processing tasks, such as data preprocessing, text classification, and sentiment analysis.