Transformer Models and NLP Tokenization
26 repos
Libraries, implementations, and tools for building and working with transformer-based language models, particularly BERT and LLM architectures. Repositories here focus on tokenization pipelines, model adaptation techniques, transformer implementations from scratch, and fine-tuning frameworks that enable efficient use of large language models across different tasks and hardware constraints.
Python · 16
Jupyter Notebook · 9
bert ·38,126
nlp ·38,126
transformers ·27,858
llama ·22,890
llm ·15,905
compression ·14,176
information-extraction ·13,586
sentiment-analysis ·12,978
distributed-training ·12,977
document-intelligence ·12,977
