{"library":"rotary-embedding-torch","type":"library","category":null,"description":"This library provides a Pytorch implementation of the Rotary Positional Embedding (RoPE), a crucial component for modern transformer architectures like LLaMA, designed to improve the model's ability to handle long sequences. It offers an easy-to-use API to apply rotary embeddings to query and key tensors. The current version is 0.8.9, and it follows a rapid release cadence for bug fixes and minor improvements.","language":"python","status":"active","version":"0.8.9","tags":["pytorch","deep-learning","transformer","attention","positional-embedding","rope"],"install":[{"cmd":"pip install rotary-embedding-torch","imports":["from rotary_embedding_torch import RotaryEmbedding"]}],"homepage":null,"github":"https://github.com/lucidrains/rotary-embedding-torch","docs":null,"changelog":null,"pypi":"https://pypi.org/project/rotary-embedding-torch/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":40,"avg_install_s":67.1,"avg_import_s":5.39,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/rotary-embedding-torch/compatibility"},"provenance":{"verified_status":"passing","verified_at":"Sun Jun 28","last_verified":"Sun Jun 28","next_check":"Tue Jul 28","install_tag":null}}