{"library":"lm-dataformat","type":"library","category":null,"description":"LM Dataformat (lm-dataformat) is a Python utility designed for efficient storage and reading of files specifically tailored for large language model (LLM) training. It provides functionalities to archive data with associated metadata and stream documents for processing. The current version is 0.0.20, but the project appears to be abandoned, with no active development or maintenance since its last release in 2021 and last GitHub commit over six years ago.","language":"python","status":"abandoned","version":"0.0.20","tags":["LLM","data storage","data format","archive","natural language processing"],"last_verified":"Tue May 26","install":[{"cmd":"pip install lm-dataformat","imports":["from lm_dataformat import Archive","from lm_dataformat import Reader"]}],"homepage":null,"github":"https://github.com/leogao2/lm_dataformat","docs":null,"changelog":null,"pypi":"https://pypi.org/project/lm-dataformat/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":100,"avg_install_s":2.1,"avg_import_s":0.15,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/lm-dataformat/compatibility"}}