{"id":13456238,"url":"https://github.com/DAMO-NLP-SG/LLM-Zoo","last_synced_at":"2025-03-24T09:31:45.531Z","repository":{"id":160786970,"uuid":"633667787","full_name":"DAMO-NLP-SG/LLM-Zoo","owner":"DAMO-NLP-SG","description":"LLM Zoo collects information of various open- and close-sourced LLMs","archived":false,"fork":false,"pushed_at":"2023-08-23T09:04:29.000Z","size":109,"stargazers_count":272,"open_issues_count":0,"forks_count":13,"subscribers_count":9,"default_branch":"main","last_synced_at":"2025-03-16T00:05:03.130Z","etag":null,"topics":["chatgpt","large-language-models","llama","llm"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DAMO-NLP-SG.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-04-28T02:39:36.000Z","updated_at":"2025-02-16T12:48:27.000Z","dependencies_parsed_at":"2024-09-04T09:40:31.260Z","dependency_job_id":null,"html_url":"https://github.com/DAMO-NLP-SG/LLM-Zoo","commit_stats":{"total_commits":38,"total_committers":6,"mean_commits":6.333333333333333,"dds":0.1842105263157895,"last_synced_commit":"a55ee01d9c01c46dae4fc1a9cd99b3ab150dbcb6"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DAMO-NLP-SG%2FLLM-Zoo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DAMO-NLP-SG%2FLLM-Zoo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DAMO-NLP-SG%2FLLM-Zoo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DAMO-NLP-SG%2FLLM-Zoo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DAMO-NLP-SG","download_url":"https://codeload.github.com/DAMO-NLP-SG/LLM-Zoo/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245036443,"owners_count":20550715,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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"}},"keywords":["chatgpt","large-language-models","llama","llm"],"created_at":"2024-07-31T08:01:18.347Z","updated_at":"2025-03-24T09:31:45.524Z","avatar_url":"https://github.com/DAMO-NLP-SG.png","language":null,"funding_links":[],"categories":["Others","A01_文本生成_文本对话"],"sub_categories":["大语言对话模型及数据"],"readme":"# 🏰 LLM Zoo\n\nAs new animal species are being discovered in the world of natural language processing (NLP) 🌍 every day, it becomes necessary to establish a zoo 🦁 to accommodate them.\n\nThis project collects below information of various open- and closed-source LLMs (after the release of ChatGPT):\n\n- Release time\n- Model size\n- Languages supported\n- Domain\n- Training data\n- Links to resources: GitHub, HuggingFace, Demo, Paper, Official blog\n\n## 📰 News\n\n- [2023.05.03] First release! We will regularly update 🔄 the repository to keep track of the latest LLMs. We welcome 👐 any contributions to this project. Please feel free to open an issue or submit a pull request to include new LLMs or update the information of existing LLMs 🙏.\n\n## 📖 Open-Sourced LLMs\n\n| Release Time | Model        | Version                        | Size           | Backbone           | Langs          | Domain   | Training Data                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               | GitHub                                                             | HF                                                                              | Paper                                      | Demo                                                             | Official Blog                                                                                                   |\n| :------------: | :------------: | :------------------------------: | :--------------: | :------------------: | :--------------: | :--------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------: | :-------------------------------------------------------------------------------: | :------------------------------------------: | :----------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------: |\n| 2023.02.27   | LLaMA        | llama-7b/13b/33b/65b           | 7B/13B/33B/65B | \\-                 | en             | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003e1T tokens (English CommonCrawl, C4, Github, Wikipedia, Gutenberg and Books3, ArXiv, Stack Exchange)\u003c/details\u003e                                                                                                                                                                                                                                                                                                                                                                                                      | [[link](https://github.com/facebookresearch/llama)]                | [[link](https://huggingface.co/decapoda-research/llama-7b-hf)]                  | [[link](https://arxiv.org/abs/2302.13971)] | \\-                                                               | [[link](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/)]                                      |\n| 2023.03.13   | Alpaca       | alpaca-7b/13b                  | 7B/13B         | LLaMA              | en             | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003e52k instruction-following data generated by InstructGPT [[link](https://github.com/tatsu-lab/stanford_alpaca/blob/main/alpaca_data.json)]\u003c/details\u003e                                                                                                                                                                                                                                                                                                                                                                | [[link](https://github.com/tatsu-lab/stanford_alpaca)]             | [[link](https://huggingface.co/tatsu-lab/alpaca-7b-wdiff)]                      | \\-                                         | [[link](https://alpaca-ai.ngrok.io/)]                            | [[link](https://crfm.stanford.edu/2023/03/13/alpaca.html)]                                                      |\n| 2023.03.13   | Vicuna       | vicuna-7b/13b-delta-v1.1       | 7B/13B         | LLaMA              | en             | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003e70K samples from sharedGPT\u003c/details\u003e                                                                                                                                                                                                                                                                                                                                                                                                                                                                               | [[link](https://github.com/lm-sys/FastChat)]                       | [[link](https://huggingface.co/lmsys/vicuna-7b-delta-v1.1)]                     | \\-                                         | [[link](https://chat.lmsys.org/)]                                | [[link](https://vicuna.lmsys.org/)]                                                                             |\n| 2023.03.14   | ChatGLM      | chatglm-6b                     | 6B             | GLM                | zh, en         | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003esupervised fine-tuning, feedback bootstrap, and reinforcement learning with human feedback\u003c/details\u003e                                                                                                                                                                                                                                                                                                                                                                                                               | [[link](https://github.com/THUDM/ChatGLM-6B)]                      | [[link](https://huggingface.co/THUDM/chatglm-6b)]                               | \\-                                         | \\-                                                               | [[link](https://chatglm.cn/blog)]                                                                               |\n| 2023.03.14   | ChatGLM      | chatglm-130b                   | 130B           | GLM                | zh, en         | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003esupervised fine-tuning, feedback bootstrap, and reinforcement learning with human feedback\u003c/details\u003e                                                                                                                                                                                                                                                                                                                                                                                                               | [[link](https://github.com/THUDM/GLM-130B)]                        | \\-                                                                              | [[link](https://arxiv.org/abs/2210.02414)] | [[link](https://chatglm.cn/login?redirect=%2F)]                  | [[link](https://chatglm.cn/blog)]                                                                               |\n| 2023.03.16   | Guanaco      | \\-                             | 7B             | LLaMA              | ja, zh, en, de | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003emultilingual datasets [[link](https://huggingface.co/datasets/JosephusCheung/GuanacoDataset)]\u003c/details\u003e                                                                                                                                                                                                                                                                                                                                                                                                            | [[link](https://github.com/Guanaco-Model/Guanaco-Model.github.io)] | [[link](https://huggingface.co/JosephusCheung/Guanaco)]                         | \\-                                         | \\-                                                               | \\-                                                                                                              |\n| 2023.03.24   | Dolly        | dolly-v1-6b                    | 6B             | GPT-J-6B           | en             | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003e52k stanford alpaca instruction-following data [[link](https://github.com/tatsu-lab/stanford_alpaca/blob/main/alpaca_data.json)]\u003c/details\u003e                                                                                                                                                                                                                                                                                                                                                                         | \\-                                                                 | [[link](https://huggingface.co/databricks/dolly-v1-6b)]                         | \\-                                         | \\-                                                               | [[link](https://www.databricks.com/blog/2023/03/24/hello-dolly-democratizing-magic-chatgpt-open-models.html)]   |\n| 2023.03.24   | ChatDoctor   | \\-                             | 7B             | LLaMA              | en             | Medicine | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003e52K stanford alpaca [[link](https://github.com/tatsu-lab/stanford_alpaca/blob/main/alpaca_data.json)], 100K HealthCareMagic [[link](https://drive.google.com/file/d/1lyfqIwlLSClhgrCutWuEe_IACNq6XNUt/view)], 10K icliniq [[link](https://drive.google.com/file/d/1ZKbqgYqWc7DJHs3N9TQYQVPdDQmZaClA/view)], 5K GenMedGPT-5k [[link](https://drive.google.com/file/d/1nDTKZ3wZbZWTkFMBkxlamrzbNz0frugg/view)]\u003c/details\u003e                                                                                             | [[link](https://github.com/Kent0n-Li/ChatDoctor)]                  | \\-                                                                              | [[link](https://arxiv.org/abs/2303.14070)] | [[link](https://huggingface.co/spaces/kenton-li/chatdoctor_csv)] | \\-                                                                                                              |\n| 2023.03.25   | LuoTuo       | Chinese-alpaca-lora            | 7B             | LLaMA              | zh, en         | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003eTranslated 52k stanford alpaca instruction-following data [[link](https://github.com/tatsu-lab/stanford_alpaca/blob/main/alpaca_data.json)], guanaco [[link](https://huggingface.co/datasets/JosephusCheung/GuanacoDataset)]\u003c/details\u003e                                                                                                                                                                                                                                                                             | [[link](https://github.com/LC1332/Chinese-alpaca-lora)]            | [[link](https://huggingface.co/silk-road/luotuo-lora-7b-1.0)]                   | \\-                                         | \\-                                                               | \\-                                                                                                              |\n| 2023.03.26   | BELLE        | BELLE-7B-0.2M/0.6M/1M/2M       | 7B             | BLOOMZ-7B1-mt      | zh, en         | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003e0.2M/0.6M/1M/2M Chinese data [[link](https://github.com/LianjiaTech/BELLE/tree/main/data)], 52k stanford alpaca instruction-following data [[link](https://github.com/tatsu-lab/stanford_alpaca/blob/main/alpaca_data.json)]\u003c/details\u003e                                                                                                                                                                                                                                                                             | [[link](https://github.com/LianjiaTech/BELLE)]                     | [[link](https://huggingface.co/BelleGroup/BELLE-7B-0.2M)]                       | [[link](https://arxiv.org/abs/2303.14742)] | \\-                                                               | \\-                                                                                                              |\n| 2023.03.28   | Linly (伶荔)   | Linly-Chinese-LLaMA 7b/13b/33b | 7B/13B/33B     | LLaMA              | zh             | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003eChinese-English parallel corpora [[link](https://statmt.org/wmt18/translation-task.html#download)], Chinese Wikipedia, community interaction, news data [[link](https://github.com/CLUEbenchmark/CLUECorpus2020)], scientific literature [[link](https://github.com/ydli-ai/CSL)]\u003c/details\u003e                                                                                                                                                                                                                        | [[link](https://github.com/CVI-SZU/Linly)]                         | [[link](https://huggingface.co/P01son/Linly-Chinese-LLaMA-7b-hf)]               | \\-                                         | \\-                                                               | \\-                                                                                                              |\n| 2023.03.28   | Linly (伶荔)   | Linly-ChatFlow 7b/13b          | 7B/13B         | LLaMA              | zh             | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003eBELLE [[link](https://github.com/LianjiaTech/BELLE)], pCLUE [[link](https://github.com/CLUEbenchmark/pCLUE)], CSL [[link](https://github.com/ydli-ai/CSL)], GuanacoDataset [[link](https://huggingface.co/datasets/JosephusCheung/GuanacoDataset)], Chain-of-Thought [[link](https://github.com/CVI-SZU/Linly/tree/main/instructions)], news_commentary [[link](https://github.com/CVI-SZU/Linly/tree/main/instructions)], firefly [[link](https://huggingface.co/datasets/YeungNLP/firefly-train-1.1M)]\u003c/details\u003e | [[link](https://github.com/CVI-SZU/Linly)]                         | [[link](https://huggingface.co/P01son/Linly-ChatFlow-13b-hf)]                   | \\-                                         | \\-                                                               | [[link](https://zhuanlan.zhihu.com/p/616748134)]                                                                |\n| 2023.04.01   | BAIZE        | baize-7B/13B/30B               | 7B/13B/30B     | LLaMA              | en             | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003e52K Stanford Alpaca [[link](https://github.com/tatsu-lab/stanford_alpaca/blob/main/alpaca_data.json)], 54K Quora [[link](https://github.com/project-baize/baize-chatbot/blob/main/data/quora_chat_data.json)], 57K StackOverFlow [[link](https://github.com/project-baize/baize-chatbot/blob/main/data/stackoverflow_chat_data.json)]\u003c/details\u003e                                                                                                                                                                    | [[link](https://github.com/project-baize/baize-chatbot)]           | [[link](https://huggingface.co/project-baize/baize-lora-7B)]                    | [[link](https://arxiv.org/abs/2304.01196)] | [[link](https://huggingface.co/spaces/project-baize/Baize-7B)]   | \\-                                                                                                              |\n| 2023.04.03   | Koala        | \\-                             | 13B            | LLaMA              | en             | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003eShareGPT, HC3 [[link](https://arxiv.org/abs/2301.07597)], OIG [[link](https://laion.ai/blog/oig-dataset/)], Stanford alpaca [[link](https://github.com/tatsu-lab/stanford_alpaca/blob/main/alpaca_data.json)], Anthropic HH [[link](https://huggingface.co/datasets/Anthropic/hh-rlhf)], OpenAI WebGPT [[link](https://huggingface.co/datasets/openai/webgpt_comparisons)], OpenAI Summarization [[link](https://huggingface.co/datasets/openai/summarize_from_feedback)]\u003c/details\u003e                                | \\-                                                                 | [[link](https://huggingface.co/young-geng/koala)]                               | \\-                                         | [[link](https://chat.lmsys.org/)]                                | [[link](https://bair.berkeley.edu/blog/2023/04/03/koala/)]                                                      |\n| 2023.04.03   | BAIZE        | baize-healthcare-7b            | 7B             | LLaMA              | en             | Medicine | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003e54K Quora [[link](https://github.com/project-baize/baize-chatbot/blob/main/data/quora_chat_data.json)], 47K medical dialogs [[link](https://github.com/project-baize/baize-chatbot/blob/main/data/medical_chat_data.json)]\u003c/details\u003e                                                                                                                                                                                                                                                                               | [[link](https://github.com/project-baize/baize-chatbot)]           | [[link](https://huggingface.co/project-baize/baize-healthcare-lora-7B)]         | \\-                                         | \\-                                                               | \\-                                                                                                              |\n| 2023.04.06   | Firefly (流萤) | firefly-1b4/2b6                | 1.4B/2.6B      | BLOOM-ZH           | zh             | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003eChinese question-answering pairs [[link](https://huggingface.co/datasets/YeungNLP/firefly-train-1.1M)], [[link](https://huggingface.co/datasets/BelleGroup/train_0.5M_CN)]\u003c/details\u003e                                                                                                                                                                                                                                                                                                                               | [[link](https://github.com/yangjianxin1/Firefly)]                  | [[link](https://huggingface.co/YeungNLP/firefly-2b6)]                           | \\-                                         | \\-                                                               | \\-                                                                                                              |\n| 2023.04.08   | Phoenix      | Phoenix-chat-7b                | 7B             | BLOOMZ             | multi          | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003econversation data [[link](https://huggingface.co/datasets/FreedomIntelligence/phoenix-sft-data-v1)]\u003c/details\u003e                                                                                                                                                                                                                                                                                                                                                                                                      | [[link](https://github.com/FreedomIntelligence/LLMZoo)]            | [[link](https://huggingface.co/FreedomIntelligence/phoenix-chat-7b)]            | \\-                                         | \\-                                                               | \\-                                                                                                              |\n| 2023.04.09   | Phoenix      | Phoenix-inst-chat-7b           | 7B             | BLOOMZ             | multi          | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003econversation data [[link](https://huggingface.co/datasets/FreedomIntelligence/phoenix-sft-data-v1)], instruction data\u003c/details\u003e                                                                                                                                                                                                                                                                                                                                                                                    | [[link](https://github.com/FreedomIntelligence/LLMZoo)]            | [[link](https://huggingface.co/FreedomIntelligence/phoenix-inst-chat-7b)]       | \\-                                         | \\-                                                               | \\-                                                                                                              |\n| 2023.04.10   | Chimera      | chimera-chat-7b/13b            | 7B/13B         | LLaMA              | latin          | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003econversation data [[link](https://huggingface.co/datasets/FreedomIntelligence/phoenix-sft-data-v1)]\u003c/details\u003e                                                                                                                                                                                                                                                                                                                                                                                                      | [[link](https://github.com/FreedomIntelligence/LLMZoo)]            | [[link](https://huggingface.co/FreedomIntelligence/chimera-chat-7b-delta)]      | \\-                                         | \\-                                                               | \\-                                                                                                              |\n| 2023.04.11   | Chimera      | chimera-inst-chat-7b/13b       | 7B/13B         | LLaMA              | latin          | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003econversation data [[link](https://huggingface.co/datasets/FreedomIntelligence/phoenix-sft-data-v1)], instruction data\u003c/details\u003e                                                                                                                                                                                                                                                                                                                                                                                    | [[link](https://github.com/FreedomIntelligence/LLMZoo)]            | [[link](https://huggingface.co/FreedomIntelligence/chimera-inst-chat-7b-delta)] | \\-                                         | \\-                                                               | \\-                                                                                                              |\n| 2023.04.12   | Dolly        | dolly-v2-12b                   | 12B            | pythia-12b         | en             | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003e15k human-generated prompt/response pairs [[link](https://huggingface.co/datasets/databricks/databricks-dolly-15k)]\u003c/details\u003e                                                                                                                                                                                                                                                                                                                                                                                      | [[link](https://github.com/databrickslabs/dolly)]                  | [[link](https://huggingface.co/databricks/dolly-v2-12b)]                        | \\-                                         | \\-                                                               | [[link](https://www.databricks.com/blog/2023/04/12/dolly-first-open-commercially-viable-instruction-tuned-llm)] |\n| 2023.04.14   | MedAlpaca    | medalpaca 7b/13b               | 7B/13B         | LLaMA              | en             | Medicine | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003equestion-answering pairs from flash card, wikidoc, stackexchange and ChatDoctor\u003c/details\u003e                                                                                                                                                                                                                                                                                                                                                                                                                          | [[link](https://github.com/kbressem/medAlpaca)]                    | [[link](https://huggingface.co/medalpaca/medalpaca-7b)]                         | [[link](https://arxiv.org/abs/2304.08247)] | \\-                                                               | \\-                                                                                                              |\n| 2023.04.19   | BELLE        | BELLE-LLaMA-7B/13B-2M          | 7B/13B         | LLaMA              | zh, en         | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003e2M Chinese data [[link](https://github.com/LianjiaTech/BELLE/tree/main/data)], 52k stanford alpaca instruction-following data [[link](https://github.com/tatsu-lab/stanford_alpaca/blob/main/alpaca_data.json)]\u003c/details\u003e                                                                                                                                                                                                                                                                                          | [[link](https://github.com/LianjiaTech/BELLE)]                     | [[link](https://huggingface.co/BelleGroup/BELLE-LLaMA-7B-2M-enc)]               | [[link](https://arxiv.org/abs/2303.14742)] | \\-                                                               | \\-                                                                                                              |\n| 2023.04.21   | MOSS         | moss-moon-003-base             | 16B            | CodeGen            | zh, en         | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003e100B Chinese tokens and 20B English tokens\u003c/details\u003e                                                                                                                                                                                                                                                                                                                                                                                                                                                               | [[link](https://github.com/OpenLMLab/MOSS)]                        | [[link](https://huggingface.co/fnlp/moss-moon-003-base)]                        | \\-                                         | [[link](https://moss.fastnlp.top/)]                              | [[link](https://txsun1997.github.io/blogs/moss.html)]                                                           |\n| 2023.04.21   | MOSS         | moss-moon-003-sft              | 16B            | moss-moon-003-base | zh, en         | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003e1.1M multi-turn conversational data (generated from ChatGPT) [[link](https://github.com/OpenLMLab/MOSS/tree/main/SFT_data/conversations/conversation_without_plugins)]\u003c/details\u003e                                                                                                                                                                                                                                                                                                                                   | [[link](https://github.com/OpenLMLab/MOSS)]                        | [[link](https://huggingface.co/fnlp/moss-moon-003-sft)]                         | \\-                                         | [[link](https://moss.fastnlp.top/)]                              | [[link](https://txsun1997.github.io/blogs/moss.html)]                                                           |\n| 2023.04.21   | MOSS         | moss-moon-003-sft-plugin       | 16B            | moss-moon-003-base | zh, en         | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003e1.1M multi-turn conversational data [[link](https://github.com/OpenLMLab/MOSS/tree/main/SFT_data/conversations/conversation_without_plugins)], 300K plugin-augmented data (generated by InstructGPT) [[link](https://github.com/OpenLMLab/MOSS/tree/main/SFT_data/conversations/conversation_with_plugins)]\u003c/details\u003e                                                                                                                                                                                              | [[link](https://github.com/OpenLMLab/MOSS)]                        | [[link](https://huggingface.co/fnlp/moss-moon-003-sft-plugin)]                  | \\-                                         | [[link](https://moss.fastnlp.top/)]                              | [[link](https://txsun1997.github.io/blogs/moss.html)]                                                           |\n| 2023.04.22   | HuggingChat  | oasst-sft-6-llama-30b          | 30B            | LLaMA              | multi          | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003ehuman-generated, human-annotated assistant-style conversation corpus consisting of 161k messages in 35 languages [[link](https://huggingface.co/datasets/OpenAssistant/oasst1)]\u003c/details\u003e                                                                                                                                                                                                                                                                                                                          | [[link](https://github.com/LAION-AI/Open-Assistant)]               | [[link](https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor)]        | \\-                                         | [[link](https://huggingface.co/chat/)]                           | \\-                                                                                                              |\n| 2023.06.19   | KnowLM  | zhixi-13b          | 13B            | LLaMA             | zh, en         | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003ehuman-generated, machine-generated and Knowledge Graph-generated in Chinese and English [[link](https://huggingface.co/datasets/OpenAssistant/oasst1)]\u003c/details\u003e                                                                                                                                                                                                                                                                                                                          | [[link](https://github.com/zjunlp/KnowLM)]               | [[link](https://huggingface.co/zjunlp/zhixi-13b-diff)]        | \\-                                         | \\-                          | \\-                                                                                                              |\n| 2023.06.21   | BayLing(百聆)  | BayLing-7b/13b          | 7B/13B            | LLaMA             | zh, en         | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003e160K human-generated, machine-generated multi-turn interactive translation corpus, alpaca instructions and sharegpt conversations [[link](https://github.com/ictnlp/BayLing)]\u003c/details\u003e                                                                                                                                                                                                                                                                                                                          | [[link](https://github.com/ictnlp/BayLing)]               | [[link](https://huggingface.co/ICTNLP/bayling-13b-v1.1)]        |  [[link](https://arxiv.org/abs/2306.10968)]                                        |  [[link](http://nlp.ict.ac.cn/bayling/demo)]                          | [[link](http://nlp.ict.ac.cn/bayling)]                                                                                                              |\n| 2023.07.18   | LLaMA 2        | llama-2-7b/13b/70b-(chat)           | 7B/13B/70B | \\-                 | en             | General  | \u003cdetails\u003e\u003csummary\u003e\u003cb\u003edetail\u003c/b\u003e\u003c/summary\u003e2T tokens (Most in English, a new mix of data from publicly available sources)\u003c/details\u003e                                                                                                                                                                                                                                                                                                                                                                                                      | [[link](https://github.com/facebookresearch/llama)]                | [[link](https://huggingface.co/meta-llama)]                  | [[link](https://scontent-hkg4-1.xx.fbcdn.net/v/t39.2365-6/10000000_662098952474184_2584067087619170692_n.pdf?_nc_cat=105\u0026ccb=1-7\u0026_nc_sid=3c67a6\u0026_nc_ohc=SvLw337Y0sQAX87v4v0\u0026_nc_ht=scontent-hkg4-1.xx\u0026oh=00_AfDsUaFec_5aYbIxirPYP2RaDQTDGrpukyDQrbI0wB1trA\u0026oe=64CE38FF)] | \\-                                                               | [[link](https://ai.meta.com/llama/)]                                      |\n\n\n## 📕 Closed-Sourced LLMs\n\n| Release Time | Model | Version | Size | Langs | Domain | Demo | Official Blog | Paper |\n| :----------: | :---: | :-----: | :---:| :---: | :----: | :----: | :---: | :---: |\n| 2022.11.30 | ChatGPT | gpt-3.5-turbo | \\- | multi | general | [[link](https://chat.openai.com/)] | [[link](https://openai.com/blog/chatgpt)] | \\- |\n| 2023.03.14 | Claude | Claude Instant\u003c/br\u003eClaude-v1 | \\- | multi | general | [[link](http://www.poe.com/)] | [[link](https://www.anthropic.com/index/introducing-claude)] | \\- |\n| 2023.03.14 | GPT | gpt-4 | \\- | multi | general | [[link](https://chat.openai.com/)] | [[link](https://openai.com/research/gpt-4)] | [[link](https://arxiv.org/abs/2303.08774)] |\n| 2023.03.16 | Ernie Bot (文心一言) | \\- | \\- | zh, en | general | [[link](https://yiyan.baidu.com/)] | [[link](https://yiyan.baidu.com/welcome)] | \\- |\n| 2023.03.21 | Bard | \\- | \\- | multi | general | [[link](https://bard.google.com/)] | [[link](https://blog.google/technology/ai/bard-google-ai-search-updates/)] | \\- |\n| 2023.03.30 | BloombergGPT | \\- | 50B | en | finance | \\- | [[link](https://www.bloomberg.com/company/press/bloomberggpt-50-billion-parameter-llm-tuned-finance/)] | [[link](https://arxiv.org/abs/2303.17564)] |\n| 2023.04.11 | Tongyi Qianwen (通义千问) | \\- | \\- | multi | general | [[link](https://tongyi.aliyun.com/)] | [[link](https://tongyi.aliyun.com/)] | \\- |\n| 2023.07.07 | OmModel（欧姆大模型） | \\- | \\- | multi | general | [[link](https://om.linker.cc)] | [[link](https://om.linker.cc)] | \\- |\n| 2023.07.11 | Claude 2 | Claude-v2 | \\- | multi | general | \\- | [[link](https://www.anthropic.com/index/claude-2)] | [[link](https://www-files.anthropic.com/production/images/Model-Card-Claude-2.pdf)] |\n\n## 🏗 TODO List\n\n- [x] Include open-sourced LLMs\n- [x] Include closed-sourced LLMs\n- [ ] Include a systematic review of common training data\n- [ ] Include interesting use cases of various LLMs\n- [ ] Performance of LLMs on various evaluation tasks\n\n## 📝 Citation\n\nIf you find this repository useful, please consider citing.\n\n```\n@software{li2023llmzoo,\n  title = {LLM Zoo}\n  author = {Li, Xingxuan and Zhang, Wenxuan and Bing, Lidong},\n  url = {https://github.com/DAMO-NLP-SG/LLM-Zoo},\n  year = {2023}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FDAMO-NLP-SG%2FLLM-Zoo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FDAMO-NLP-SG%2FLLM-Zoo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FDAMO-NLP-SG%2FLLM-Zoo/lists"}