Pre-trained Language Models & Inference

8 repos

Implementations and deployments of large language models (LLMs) including OPT variants, GPT-2 adaptations, and CodeGPT models, with a focus on inference optimization and serving. The cluster centers on frameworks like Transformers and PyTorch for running and fine-tuning these models, plus specialized tools for efficient text generation inference. Repositories here span model checkpoints, language-specific variants (Chinese, Java), and the infrastructure for deploying these models at scale.

Related clusters