{"payload":{"header_redesign_enabled":false,"results":[{"id":"631152162","archived":false,"color":"#3572A5","followers":206,"has_funding_file":false,"hl_name":"jackaduma/Vicuna-LoRA-RLHF-PyTorch","hl_trunc_description":"A full pipeline to finetune Vicuna LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human…","language":"Python","mirror":false,"owned_by_organization":false,"public":true,"repo":{"repository":{"id":631152162,"name":"Vicuna-LoRA-RLHF-PyTorch","owner_id":1276942,"owner_login":"jackaduma","updated_at":"2024-05-20T13:10:39.062Z","has_issues":true}},"sponsorable":false,"topics":["pytorch","llama","gpt","lora","finetune","ppo","peft","vicuna","llm","chatgpt","rlhf","reward-models","vicuna-7b"],"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":66,"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%253Ajackaduma%252FVicuna-LoRA-RLHF-PyTorch%2B%2Blanguage%253APython","metadata":null,"warn_limited_results":false,"csrf_tokens":{"/jackaduma/Vicuna-LoRA-RLHF-PyTorch/star":{"post":"2XW2c4Q1Ktu9h0gr7l3rzpDtGWhhBSkGuiKeh0EAjrL_0UAeA3McDLcRJ4CynLoUzIOVn6MzJxgEvk_hJcMaUw"},"/jackaduma/Vicuna-LoRA-RLHF-PyTorch/unstar":{"post":"LmWc8gIrZ0xwmOFZ4yKjOlHYXQuSSMs4dT1cZ0y1mxvXs_PN7bcc1EP0-0Hn9apCD2RxOY8v2QUhQtu-8awVpQ"},"/sponsors/batch_deferred_sponsor_buttons":{"post":"NDM3m-HuyR5yt_MkDF7Eep9znVIZvxtOGmJD1K3W_dGi9sB9Oep8jhqTaV6CqVx46xuz-Vi-Ok0oO0_NnbR5oA"}}},"title":"Repository search results"}