Google Cloud TPU Utilization Bar for Training Models

🔎 Monitor deep learning model training and hardware usage from your mobile phone 📱

Customizable implementation of the self-instruct paper.

An Experiment on Dynamic NTK Scaling RoPE

Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

Make your own story. User-friendly software for LLM roleplaying

JAX implementation of the Llama 2 model

Inference Llama 2 in one file of pure C