{"payload":{"header_redesign_enabled":false,"results":[{"id":"663944322","archived":false,"color":"#DA5B0B","followers":33,"has_funding_file":false,"hl_name":"michaelnny/InstructLLaMA","hl_trunc_description":"Implements pre-training, supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF), to train and fine-tune the …","language":"Jupyter Notebook","mirror":false,"owned_by_organization":false,"public":true,"repo":{"repository":{"id":663944322,"name":"InstructLLaMA","owner_id":56952187,"owner_login":"michaelnny","updated_at":"2024-03-09T15:39:45.166Z","has_issues":true}},"sponsorable":false,"topics":["ppo","rhlf","instructgpt","qlora","llam2","4bit-fine-tune"],"type":"Public","help_wanted_issues_count":0,"good_first_issue_issues_count":0,"starred_by_current_user":false}],"type":"repositories","page":1,"page_count":1,"elapsed_millis":51,"errors":[],"result_count":1,"facets":[],"protected_org_logins":[],"topics":null,"query_id":"","logged_in":false,"sign_up_path":"/signup?source=code_search_results","sign_in_path":"/login?return_to=https%3A%2F%2Fgithub.com%2Fsearch%3Fq%3Drepo%253Amichaelnny%252FInstructLLaMA%2B%2Blanguage%253A%2522Jupyter%2BNotebook%2522","metadata":null,"csrf_tokens":{"/michaelnny/InstructLLaMA/star":{"post":"550eIjo-9RZ1dUQw0lynokCHbywUAeCG9-DYcp2YxT5PNrvHAr9YUKVxNJuthMXM1j_uI_QHWbYfYmS2vxA5Rw"},"/michaelnny/InstructLLaMA/unstar":{"post":"YCC7XrxcpSd89_j9F-rXzkmXojahgMf-YI8-Gf-Xgj92JnIe0ej6C7d5w3bH21N5qxClnj4f-oOGfRD_bpxiXA"},"/sponsors/batch_deferred_sponsor_buttons":{"post":"vwXULY9FgR9HCsQCVkTWy9kZjiSyL4TZ-G9bYMQz8fBadbIvokpuzA3kZYTbR1LlAkDVHSJH92pD5RHLn6_roA"}}},"title":"Repository search results"}