{
    "multi-alpaca": {
        "dataset_id": "damo/nlp_polylm_multialpaca_sft",
        "subsets": ["ar", "de", "es", "fr", "id", "ja", "ko", "pt", "ru", "th", "vi"],
        "tags": ["chat", "general", "multilingual"]
    },
    "text2sql-en": {
        "dataset_id": "AI-ModelScope/texttosqlv2_25000_v2",
        "tags": ["chat", "sql"],
        "hf_dataset_id": "Clinton/texttosqlv2_25000_v2"
    },
    "school-math-zh": {
        "dataset_id": "AI-ModelScope/school_math_0.25M",
        "tags": ["chat", "math"],
        "hf_dataset_id": "BelleGroup/school_math_0.25M"
    },
    "gpt4all-en": {
        "dataset_id": "wyj123456/GPT4all",
        "tags": ["chat", "general"]
    },
    "cot-zh": {
        "dataset_id": "YorickHe/CoT_zh",
        "tags": ["chat", "general"]
    },
    "cot-en": {
        "dataset_id": "YorickHe/CoT",
        "tags": ["chat", "general"]
    },
    "instinwild": {
        "dataset_id": "wyj123456/instinwild",
        "subsets": ["default", "subset"],
        "tag": ["chat", "general"],
        "help": "`default` is in Chinese, `subset` is in English."
    },
    "code-alpaca-en": {
        "dataset_id": "wyj123456/code_alpaca_en",
        "tag": ["chat", "coding"],
        "hf_dataset_id": "sahil2801/CodeAlpaca-20k"
    },
    "finance-en": {
        "dataset_id": "wyj123456/finance_en",
        "tags": ["chat", "financial"],
        "hf_dataset_id": "ssbuild/alpaca_finance_en"
    },
    "alpaca-en": {
        "dataset_id": "AI-ModelScope/alpaca-gpt4-data-en",
        "tags": ["chat", "general", "🔥"],
        "hf_dataset_id": "vicgalle/alpaca-gpt4"
    },
    "coig-cqia": {
        "dataset_id": "AI-ModelScope/COIG-CQIA",
        "subsets": ["chinese_traditional", "coig_pc", "exam", "finance", "douban", "human_value", "logi_qa",
                    "ruozhiba", "segmentfault", "wiki", "wikihow", "xhs", "zhihu"],
        "tags": ["general", "🔥"]
    },
    "ms-agent-for-agentfabric": {
        "dataset_id": "AI-ModelScope/ms_agent_for_agentfabric",
        "subsets": ["default", "addition"],
        "tags": ["chat", "agent", "multi-round", "🔥"]
    },
    "deepctrl-sft": {
        "dataset_id": "AI-ModelScope/deepctrl-sft-data",
        "subsets": ["default", "en"],
        "tags": ["chat", "general", "sft", "multi-round"],
        "help": "`default` is in Chinese, `en` is in English."
    },
    "poetry-zh": {
        "dataset_id": "modelscope/chinese-poetry-collection",
        "split": ["test"],
        "columns": {"text1": "response"},
        "tags": ["text-generation", "poetry"]
    },
    "instruct-en": {
        "dataset_id": "wyj123456/instruct",
        "columns": {
            "prompt": "query",
            "completion": "response"
        },
        "tags": ["chat", "general"]
    },

    "cls-fudan-news-zh": {
        "dataset_id": "damo/zh_cls_fudan-news",
        "columns": {"prompt": "query", "answer": "response"},
        "tags": ["chat", "classification"]
    },
    "ner-jave-zh": {
        "dataset_id": "damo/zh_ner-JAVE",
        "columns": {"prompt": "query", "answer": "response"},
        "tags": ["chat", "ner"]
    },
    "lawyer-llama-zh": {
        "dataset_id": "AI-ModelScope/lawyer_llama_data",
        "columns": {"instruction": "query", "output": "response", "history": "-"},
        "tags": ["chat", "law"],
        "hf_dataset_id": "Skepsun/lawyer_llama_data"
    },
    "codefuse-evol-instruction-zh": {
        "dataset_id": "codefuse-ai/Evol-instruction-66k",
        "columns": {"instruction": "query", "output": "response"},
        "tags": ["chat", "coding", "🔥"]
    },
    "tulu-v2-sft-mixture": {
        "dataset_id": "AI-ModelScope/tulu-v2-sft-mixture",
        "tags": ["chat", "multilingual", "general", "multi-round"],
        "hf_dataset_id": "allenai/tulu-v2-sft-mixture"
    },
    "webnovel-zh": {
        "dataset_id": "AI-ModelScope/webnovel_cn",
        "tags": ["chat", "novel"],
        "hf_dataset_id": "zxbsmk/webnovel_cn"
    },
    "generated-chat-zh": {
        "dataset_id": "AI-ModelScope/generated_chat_0.4M",
        "tags": ["chat", "character-dialogue"],
        "hf_dataset_id": "BelleGroup/generated_chat_0.4M"
    },
    "wikipedia-zh": {
        "dataset_id": "AI-ModelScope/wikipedia-cn-20230720-filtered",
        "columns": {"completion": "response"},
        "tags": ["text-generation", "general", "pretrained"],
        "hf_dataset_id": "pleisto/wikipedia-cn-20230720-filtered"
    },
    "open-platypus-en": {
        "dataset_id": "AI-ModelScope/Open-Platypus",
        "tags": ["chat", "math"],
        "hf_dataset_id": "garage-bAInd/Open-Platypus"
    },
    "open-orca": {
        "dataset_id": "AI-ModelScope/OpenOrca",
        "subset": ["default", "3_5M"],
        "columns": {"question": "query"},
        "tags": ["chat", "multilingual", "general"],
        "help": ["`default` uses gpt4 for data cleaning."]
    },
    "disc-law-sft-zh": {
        "dataset_id": "AI-ModelScope/DISC-Law-SFT",
        "columns": {"input": "query", "output": "response"},
        "tags": ["chat", "law", "🔥"],
        "hf_dataset_id": "ShengbinYue/DISC-Law-SFT"
    },
    "pileval": {
        "dataset_id": "huangjintao/pile-val-backup",
        "columns": {"text": "response"},
        "split": ["validation"],
        "tags": ["text-generation", "awq"],
        "hf_dataset_id": "mit-han-lab/pile-val-backup"
    },
    "stack-exchange-paired": {
        "dataset_id": "AI-ModelScope/stack-exchange-paired",
        "columns": {
            "question": "query",
            "response_j": "response",
            "response_k": "rejected_response"
        },
        "tags": ["hfrl", "dpo", "pairwise"]
    },
    "ms-agent": {
        "dataset_id": "iic/ms_agent",
        "conversations": {
            "error_strategy": "delete"
        },
        "tags": ["chat", "agent", "multi-round", "🔥"]
    },
    "codefuse-python-en": {
        "dataset_id": "codefuse-ai/CodeExercise-Python-27k",
        "conversations": {
            "user_role": "human",
            "assistant_role": "bot",
            "conversations_key": "chat_rounds",
            "from_key": "role",
            "value_key": "content",
            "error_strategy": "delete"
        },
        "tags": ["chat", "coding", "🔥"]
    },
    "sharegpt-gpt4": {
        "dataset_id": "AI-ModelScope/sharegpt_gpt4",
        "subsets": ["default", "V3_format", "zh_38K_format"],
        "conversations": {
            "user_role": "human",
            "assistant_role": "gpt",
            "error_strategy": "delete"
        },
        "tags": ["chat", "multilingual", "general", "multi-round", "gpt4", "🔥"],
        "help": "`default` uses gpt4 for data cleaning."
    },
    "disc-med-sft-zh": {
        "dataset_id": "AI-ModelScope/DISC-Med-SFT",
        "conversations": {
            "conversations_key": "conversation",
            "from_key": "role",
            "value_key": "content",
            "error_strategy": "delete"
        },
        "tags": ["chat", "medical", "🔥"],
        "hf_dataset_id": "Flmc/DISC-Med-SFT"
    },
    "medical-en": {
        "dataset_id": "huangjintao/medical_zh",
        "subsets": ["en"],
        "split": ["train", "val", "test"],
        "columns": {
            "input": "query",
            "output": "response"
        },
        "tags": ["chat", "medical"]
    },
    "medical-zh": {
        "dataset_id": "huangjintao/medical_zh",
        "subsets": ["zh"],
        "split": ["train", "val", "test"],
        "columns": {
            "instruction": "query",
            "output": "response"
        },
        "tags": ["chat", "medical"]
    },
    "self-cognition": {
        "dataset_id": "swift/self-cognition",
        "hf_dataset_id": "modelscope/self-cognition",
        "remove_useless_columns": false,
        "tags": ["chat", "self-cognition", "🔥"]
    }
}