423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-14 19:06:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

improve KTO impl., replace datasets

Browse Source 
Former-commit-id: c450ee87a3
This commit is contained in:
hiyouga
2024-05-18 03:44:56 +08:00
parent 97469892c3
commit 13d7b48efe
66 changed files with 46444 additions and 28125 deletions
Download Patch File Download Diff File Expand all files Collapse all files

220
data/dataset_info.json
View File

@@ -1,48 +1,23 @@
{
"alpaca_en": {
"file_name": "alpaca_data_en_52k.json"
},
"alpaca_zh": {
"file_name": "alpaca_data_zh_51k.json"
},
"alpaca_gpt4_en": {
"file_name": "alpaca_gpt4_data_en.json"
},
"alpaca_gpt4_zh": {
"file_name": "alpaca_gpt4_data_zh.json"
},
"identity": {
"file_name": "identity.json"
},
"oaast_sft_zh": {
"file_name": "oaast_sft_zh.json",
"alpaca_en_demo": {
"file_name": "alpaca_en_demo.json"
},
"alpaca_zh_demo": {
"file_name": "alpaca_zh_demo.json"
},
"glaive_toolcall_en_demo": {
"file_name": "glaive_toolcall_en_demo.json",
"formatting": "sharegpt",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
"messages": "conversations",
"tools": "tools"
}
},
"lima": {
"file_name": "lima.json",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
}
},
"kto-mix-test": {
"file_name": "kto-mix-test.json",
"file_sha1": "91b59f657007dc4b17529fc643v9b9cd6d640fha",
"columns": {
"prompt": "instruction",
"response": "output",
"tag": "tag"
}
},
"glaive_toolcall": {
"file_name": "glaive_toolcall_10k.json",
"glaive_toolcall_zh_demo": {
"file_name": "glaive_toolcall_zh_demo.json",
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
@@ -63,15 +38,42 @@
"assistant_tag": "assistant"
}
},
"example": {
"script_url": "example_dataset",
"alpaca_en": {
"hf_hub_url": "llamafactory/alpaca_en",
"ms_hub_url": "llamafactory/alpaca_en"
},
"alpaca_zh": {
"hf_hub_url": "llamafactory/alpaca_zh",
"ms_hub_url": "llamafactory/alpaca_zh"
},
"alpaca_gpt4_en": {
"hf_hub_url": "llamafactory/alpaca_gpt4_en",
"ms_hub_url": "llamafactory/alpaca_gpt4_en"
},
"alpaca_gpt4_zh": {
"hf_hub_url": "llamafactory/alpaca_gpt4_zh",
"ms_hub_url": "llamafactory/alpaca_gpt4_zh"
},
"glaive_toolcall_en": {
"hf_hub_url": "llamafactory/glaive_toolcall_en",
"formatting": "sharegpt",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
"messages": "conversations",
"tools": "tools"
}
},
"glaive_toolcall_zh": {
"hf_hub_url": "llamafactory/glaive_toolcall_zh",
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"tools": "tools"
}
},
"lima": {
"hf_hub_url": "llamafactory/lima",
"formatting": "sharegpt"
},
"guanaco": {
"hf_hub_url": "JosephusCheung/GuanacoDataset",
"ms_hub_url": "AI-ModelScope/GuanacoDataset"
@@ -240,6 +242,12 @@
"response": "text"
}
},
"stem_zh": {
"hf_hub_url": "hfl/stem_zh_instruction"
},
"ruozhiba_gpt4": {
"hf_hub_url": "hfl/ruozhiba_gpt4_turbo"
},
"llava_150k_en": {
"hf_hub_url": "BUAADreamer/llava-en-zh-300k",
"subset": "en",
@@ -297,73 +305,105 @@
"ultrachat_de": {
"hf_hub_url": "mayflowergmbh/ultra-chat_de"
},
"hh_rlhf_en": {
"script_url": "hh_rlhf_en",
"dpo_en_demo": {
"file_name": "dpo_en_demo.json",
"ranking": true,
"formatting": "sharegpt",
"columns": {
"prompt": "instruction",
"response": "output",
"history": "history"
},
"ranking": true
"messages": "conversations",
"chosen": "chosen",
"rejected": "rejected"
}
},
"oaast_rm_zh": {
"file_name": "oaast_rm_zh.json",
"dpo_zh_demo": {
"file_name": "dpo_zh_demo.json",
"ranking": true,
"formatting": "sharegpt",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
},
"ranking": true
"messages": "conversations",
"chosen": "chosen",
"rejected": "rejected"
}
},
"comparison_gpt4_en": {
"file_name": "comparison_gpt4_data_en.json",
"ranking": true
"dpo_mix_en": {
"hf_hub_url": "hiyouga/DPO-En-Zh-20k",
"subset": "en",
"ranking": true,
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"chosen": "chosen",
"rejected": "rejected"
}
},
"comparison_gpt4_zh": {
"file_name": "comparison_gpt4_data_zh.json",
"ranking": true
"dpo_mix_zh": {
"hf_hub_url": "hiyouga/DPO-En-Zh-20k",
"subset": "zh",
"ranking": true,
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"chosen": "chosen",
"rejected": "rejected"
}
},
"orca_rlhf": {
"file_name": "orca_rlhf.json",
"orca_pairs": {
"hf_hub_url": "Intel/orca_dpo_pairs",
"ranking": true,
"columns": {
"prompt": "question",
"response": "answer",
"chosen": "chosen",
"rejected": "rejected",
"system": "system"
}
},
"hh_rlhf_en": {
"script_url": "hh_rlhf_en",
"ranking": true,
"columns": {
"prompt": "instruction",
"chosen": "chosen",
"rejected": "rejected",
"history": "history"
}
},
"nectar_rm": {
"hf_hub_url": "AstraMindAI/RLAIF-Nectar",
"ms_hub_url": "AI-ModelScope/RLAIF-Nectar",
"ranking": true
},
"dpo_mix_en": {
"hf_hub_url": "hiyouga/DPO-En-Zh-20k",
"subset": "en",
"ranking": true,
"columns": {
"prompt": "prompt",
"response": "answer",
"system": "system",
"history": "history"
}
},
"dpo_mix_zh": {
"hf_hub_url": "hiyouga/DPO-En-Zh-20k",
"subset": "zh",
"ranking": true,
"columns": {
"prompt": "prompt",
"response": "answer",
"system": "system",
"history": "history"
}
},
"orca_dpo_de": {
"hf_hub_url": "mayflowergmbh/intel_orca_dpo_pairs_de",
"ranking": true
},
"kto_en_demo": {
"file_name": "kto_en_demo.json",
"formatting": "sharegpt",
"columns": {
"messages": "messages",
"kto_tag": "label"
},
"tags": {
"role_tag": "role",
"content_tag": "content",
"user_tag": "user",
"assistant_tag": "assistant"
}
},
"kto_mix_en": {
"hf_hub_url": "argilla/kto-mix-15k",
"formatting": "sharegpt",
"columns": {
"messages": "completion",
"kto_tag": "label"
},
"tags": {
"role_tag": "role",
"content_tag": "content",
"user_tag": "user",
"assistant_tag": "assistant"
}
},
"wiki_demo": {
"file_name": "wiki_demo.txt",
"columns": {