{"full_name":"nlpxucan/WizardLM","owner":"nlpxucan","name":"WizardLM","shard":"1","url":"https://github.com/nlpxucan/WizardLM","description":"LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath","homepage":"","topics":[],"tag_pages":[],"language":"Python","license":null,"avatar":"https://avatars.githubusercontent.com/u/12636990?u=6bfb71725596fd0a242226db55ec650bd8321668&v=4","created_at":"2023-04-23T13:26:46Z","pushed_at":"2025-06-07T01:35:05Z","metrics":{"stars":9471,"forks":742,"watchers":106,"issues":194,"prs":71,"releases":6,"issues_open":163,"issues_closed":31,"prs_open":5,"prs_closed":14,"prs_merged":52,"discussions":0},"growth":{"day":{"stars":2,"forks":2,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[9471,9470,9470,9470,9469,9469,9471],"forks":[742,742,743,742,741,740,742],"watchers":[null,105,105,105,105,105,106],"issues_open":[null,163,163,163,163,163,163],"prs_open":[null,5,5,5,5,5,5]},"boards":{},"same_owner":[],"issues":[{"number":4,"title":"Remove \"As an AI language model...\" from dataset.","comments":14,"created_at":"2023-04-26T07:56:27Z"},{"number":59,"title":"78k evolved code instructions","comments":12,"created_at":"2023-06-15T08:28:39Z"},{"number":99,"title":"Licensing","comments":10,"created_at":"2023-06-28T08:25:41Z"},{"number":79,"title":"finetune on WizardCoder-15B-V1.0","comments":9,"created_at":"2023-06-20T09:04:14Z"},{"number":38,"title":"from train import smart_tokenizer_and_embedding_resize","comments":7,"created_at":"2023-05-30T19:31:40Z"},{"number":7,"title":"Model does not obey follow up instructions very well(at all), compared to Vicuna for example","comments":7,"created_at":"2023-04-26T23:11:45Z"},{"number":200,"title":"How can I use multiple GPUs for inference.","comments":6,"created_at":"2023-09-04T02:46:30Z"},{"number":140,"title":"Batch inference","comments":6,"created_at":"2023-07-31T11:16:14Z"}],"discussions":[],"latest_release":{"name":"Release v1.6","tag":"v1.6","published_at":"2023-08-27T10:47:33Z","body":"## 🚀<b>**Major Update: Introducing WizardCoder 34B trained from Code Llama**</b>\r\n\r\n<br>\r\n<b>WizardCoder-34B</b> surpasses <b>GPT-4</b>, <b>ChatGPT-3.5</b> and <b>Claude-2</b> on HumanEval with <b>73.2%</b> pass@1\r\n\r\n- 🖥️Demo: http://47.103.63.15:50085/\r\n\r\n- 🏇Model Weights: https://huggingface.co/WizardLM/WizardCoder-Python-34B-V1.0\r\n\r\n","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}