{"payload":{"header_redesign_enabled":false,"results":[{"id":"631152162","archived":false,"color":"#3572A5","followers":197,"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":64,"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,"csrf_tokens":{"/jackaduma/Vicuna-LoRA-RLHF-PyTorch/star":{"post":"rKas4Iqjhc_dkq4_C0Kf660oosVGlmW2VLyTjFlw_qoOpwZAdhp7tAYE1s2gEbtpIEjLX2RMSsnXRb3r36-dTg"},"/jackaduma/Vicuna-LoRA-RLHF-PyTorch/unstar":{"post":"esgM2EMD1TjtGAQ8aX1nM4hY60VME8lMHqhOzWQ1TYAe154vN7Tdt5hBHPw-dRHRUl8jVb_tRRPmSZA-8jVQjg"},"/sponsors/batch_deferred_sponsor_buttons":{"post":"9ia5P9gLzuuh1H61NBCm_GqNLwU7oxU3RoGVey67FIqbdOtiJ-enX2LSPHCCAxCLbnZYQLlbtI91rUF2--5h1w"}}},"title":"Repository search results"}