{"payload":{"header_redesign_enabled":false,"results":[{"id":"604237657","archived":false,"color":"#3572A5","followers":167,"has_funding_file":false,"hl_name":"tomekkorbak/pretraining-with-human-feedback","hl_trunc_description":"Code accompanying the paper Pretraining Language Models with Human Preferences","language":"Python","mirror":false,"owned_by_organization":false,"public":true,"repo":{"repository":{"id":604237657,"name":"pretraining-with-human-feedback","owner_id":9259131,"owner_login":"tomekkorbak","updated_at":"2024-02-13T03:28:45.287Z","has_issues":true}},"sponsorable":false,"topics":["reinforcement-learning","gpt","language-models","ai-safety","ai-alignment","pretraining","decision-transformers","rlhf"],"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":79,"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%253Atomekkorbak%252Fpretraining-with-human-feedback%2B%2Blanguage%253APython","metadata":null,"csrf_tokens":{"/tomekkorbak/pretraining-with-human-feedback/star":{"post":"ggY1zJs-HalcREqZIqbr3AXFRYPvZnh3rzyqXF6rhKkOcot4juUktKHuGj9gURwW5h417nCDM7YgUKzWwPjWyQ"},"/tomekkorbak/pretraining-with-human-feedback/unstar":{"post":"GWNeIh8FD2J41NzFV3M_UnGn51KHpuO5UgAf6zRPzXKAGOEs7IlP_YbTyKx1AxcWGQja6s405csFmgjq0BbBUA"},"/sponsors/batch_deferred_sponsor_buttons":{"post":"_bLC7zccgU2qse4BgL7FG-wFv2AcOeBuz3GK4b06-o0J9nwOoipVU94l5Wul382EOEDYE8nO4ZEV7IDQy_JbfQ"}}},"title":"Repository search results"}