{"id":24085,"url":"https://github.com/ariafyy/awesome_open_llms","name":"awesome_open_llms","description":"open source ChatGPT and GPT4 alternative LLMs","projects_count":37,"last_synced_at":"2026-09-04T08:00:23.369Z","repository":{"id":165154591,"uuid":"619483488","full_name":"ariafyy/awesome_open_llms","owner":"ariafyy","description":"open source ChatGPT and GPT4 alternative LLMs","archived":false,"fork":false,"pushed_at":"2023-05-26T07:30:20.000Z","size":24,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-07-27T04:04:23.200Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ariafyy.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2023-03-27T08:26:45.000Z","updated_at":"2023-03-31T08:15:54.000Z","dependencies_parsed_at":"2024-01-18T10:03:28.639Z","dependency_job_id":null,"html_url":"https://github.com/ariafyy/awesome_open_llms","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ariafyy/awesome_open_llms","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ariafyy%2Fawesome_open_llms","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ariafyy%2Fawesome_open_llms/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ariafyy%2Fawesome_open_llms/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ariafyy%2Fawesome_open_llms/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ariafyy","download_url":"https://codeload.github.com/ariafyy/awesome_open_llms/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ariafyy%2Fawesome_open_llms/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":36687381,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-08-06T04:43:03.162Z","status":"online","status_checked_at":"2026-08-15T02:00:05.847Z","response_time":94,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2024-01-13T12:56:42.381Z","updated_at":"2026-09-04T08:00:23.370Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["Chinese models","finetune blog","multi lang models","tools","multi-modal","others"],"sub_categories":["glm 6b","unsure but maybe useful"],"readme":"# Awesome_alternative_llms[![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\nopen source ChatGPT and GPT4 alternatives for LLMs\n\n \n## multi lang models\n- [FastChat](https://github.com/lm-sys/FastChat)\n\n- [Llama-X](https://github.com/AetherCortex/Llama-X)\n\n- [LLaMA-Adapter](https://github.com/ZrrSkywalker/LLaMA-Adapter)\n\n- [LLaMA-cpp](https://github.com/ggerganov/llama.cpp)\n\n- [LLAMA download](https://github.com/shawwn/llama-dl)\n\n- [stanford_alpaca](https://github.com/tatsu-lab/stanford_alpaca)\n\n- [alpaca-lora](https://github.com/tloen/alpaca-lora)\n\n- [gpt4all](https://github.com/nomic-ai/gpt4all)\n\n- [gpt4all-visualization](https://atlas.nomic.ai/map/gpt4all_data_clean_without_p3)\n\n- [timdettmers/guanaco-33b-merged-qlora download](https://huggingface.co/timdettmers/guanaco-33b-merged/tree/main)\n\n\n## Chinese models\n* [Chinese shibing624 LMFT](https://github.com/shibing624/lmft)\n\n* [Chinese luotuo](https://github.com/LC1332/Chinese-alpaca-lora)\n\n* [Chinese BELLE](https://github.com/LianjiaTech/BELLE)\n\n* [Chinese-LLaMA-Alpaca (macbert author)](https://github.com/ymcui/Chinese-LLaMA-Alpaca)\n\n* [clue-github](https://github.com/clue-ai/ChatYuan)\n\n* [clue v2-huggingface](https://huggingface.co/spaces/ClueAI/ChatYuan-large-v2)\n\n* [CLUEbenchmark](https://github.com/CLUEbenchmark)\n\n* [PromptCLUE-HF](https://huggingface.co/ClueAI/PromptCLUE-base) \n\n### glm 6b\n\n- 模型已经开源至 Hugging Face Hub，可以直接利用 HF Trainer 等进行训练；RLHF 部分，亦可以直接利用 trlx 等库进行实现\n\n* [glm6b-ptuning:P-Tuning and INT4 quantization, only requires 7GB GPU memory](https://github.com/THUDM/ChatGLM-6B/blob/main/ptuning/README.md)\n\n* [glm6b-c++ mnn onnx](https://github.com/wangzhaode/ChatGLM-MNN)\n\n#### glm6b-finetune-lora\n* [zero_nlp](https://github.com/yuanzhoulvpi2017/zero_nlp/tree/main/simple_thu_chatglm6b)\n* [lich99](https://github.com/lich99/ChatGLM-finetune-LoRA)\n* [mymusise](https://github.com/mymusise/ChatGLM-Tuning)\n* [ssbuild](https://github.com/ssbuild/chatglm_finetuning)\n* [chenyiwan](https://github.com/chenyiwan/chatglm-6b-fine-tuning)\n\n## multi-modal \n* [visual-openllm](https://github.com/visual-openllm/visual-openllm)\n\n\n## tools\n* [huggingface/peft](https://github.com/huggingface/peft)\n\n* [trlx RLHF](https://github.com/CarperAI/trlx)\n\n* [langchain](https://github.com/hwchase17/langchain)\n\n* [dataset-chinese-zbench](https://github.com/zhenbench/z-bench)\n\n* [dataset-chinese belle : can find in LianjiaTech github and HF BelleGroup](https://huggingface.co/datasets/BelleGroup/generated_train_0.5M_CN)\n\n* [dataset-chinese-pCLUE](https://github.com/CLUEbenchmark/pCLUE)\n\n## finetune blog\n* [fine-tune-alpaca-with-lora](https://replicate.com/blog/fine-tune-alpaca-with-lora?continueFlag=4ecae39885197a5c008faabbefb5c824)\n* [hugging face official blog in chinese:在一张 24 GB 的消费级显卡上用 RLHF 微调 20B LLMs ](https://zhuanlan.zhihu.com/p/616346543?utm_medium=social\u0026utm_oi=762255747382796288\u0026utm_psn=1622284420437450752\u0026utm_source=wechat_session\u0026utm_id=0)\n* [hugging face official blog :Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU ](https://huggingface.co/blog/trl-peft)\n\n\n\n \n## others\n-  内存泄漏检查: 内存分析工具: Eclipse Memory Analyzer、VisualVM\n\n### unsure but maybe useful\n能否用GLM的pretrain代码和finetune代码来做CahtGLM的continue pretrain和finetune？\nhttps://github.com/THUDM/GLM/blob/main/pretrain_glm.py\nhttps://github.com/THUDM/GLM/blob/main/finetune_glm.py\n\n-[glm issue3 ](https://github.com/THUDM/ChatGLM-6B/issues/3)\n-[glm issue67](https://github.com/THUDM/ChatGLM-6B/issues/67)\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/ariafyy%2Fawesome_open_llms/projects"}