423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-14 10:56:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

add code for reading from multi files in one directory

Browse Source 
Former-commit-id: 3dd5f9a874
This commit is contained in:
BUAADreamer
2023-06-10 15:53:47 +08:00
parent 587d7a907f
commit 53727aee3e
5 changed files with 203 additions and 158 deletions
Download Patch File Download Diff File Expand all files Collapse all files

217
data/dataset_info.json
View File

@@ -1,107 +1,116 @@
{
"alpaca_en": {
"hf_hub_url": "tatsu-lab/alpaca"
},
"alpaca_zh": {
"file_name": "alpaca_data_zh_51k.json",
"file_sha1": "e655af3db557a4197f7b0cf92e1986b08fae6311"
},
"alpaca_gpt4_en": {
"file_name": "alpaca_gpt4_data_en.json",
"file_sha1": "647f4ad447bd993e4b6b6223d1be15208bab694a"
},
"alpaca_gpt4_zh": {
"file_name": "alpaca_gpt4_data_zh.json",
"file_sha1": "3eaa3bda364ccdd59925d7448a698256c31ef845"
},
"belle_0.5m": {
"hf_hub_url": "BelleGroup/train_0.5M_CN"
},
"belle_1m": {
"hf_hub_url": "BelleGroup/train_1M_CN"
},
"belle_2m": {
"hf_hub_url": "BelleGroup/train_2M_CN"
},
"belle_dialog": {
"hf_hub_url": "BelleGroup/generated_chat_0.4M"
},
"belle_math": {
"hf_hub_url": "BelleGroup/school_math_0.25M"
},
"belle_multiturn": {
"hf_hub_url": "BelleGroup/multiturn_chat_0.8M"
},
"guanaco": {
"hf_hub_url": "JosephusCheung/GuanacoDataset"
},
"firefly": {
"hf_hub_url": "YeungNLP/firefly-train-1.1M",
"columns": {
"prompt": "input",
"query": "",
"response": "target",
"history": ""
}
},
"codealpaca": {
"hf_hub_url": "sahil2801/CodeAlpaca-20k"
},
"alpaca_cot": {
"hf_hub_url": "QingyiSi/Alpaca-CoT"
},
"webqa": {
"hf_hub_url": "suolyer/webqa",
"columns": {
"prompt": "input",
"query": "",
"response": "output",
"history": ""
}
},
"ultra_chat": {
"script_url": "ultra_chat",
"columns": {
"prompt": "instruction",
"query": "",
"response": "output",
"history": "history"
}
},
"example": {
"script_url": "example_dataset",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
}
},
"comparison_gpt4_en": {
"file_name": "comparison_gpt4_data_en.json",
"file_sha1": "eeb295ce0ab011c37af52596460c8a57d07ad19f"
},
"comparison_gpt4_zh": {
"file_name": "comparison_gpt4_data_zh.json",
"file_sha1": "b99a41c1c864019d9b0c07dbcd5df0560cf33ce0"
},
"hh_rlhf_en": {
"script_url": "hh_rlhf_en",
"columns": {
"prompt": "instruction",
"query": "",
"response": "output",
"history": "history"
}
},
"wiki_demo": {
"file_name": "wiki_demo.txt",
"file_sha1": "b2288edb05b233e5b35250fd4b308a5fa21fa66d",
"columns": {
"prompt": "text",
"query": "",
"response": "",
"history": ""
}
"alpaca_en": {
"hf_hub_url": "tatsu-lab/alpaca"
},
"alpaca_zh": {
"file_name": "alpaca_data_zh_51k.json",
"file_sha1": "e655af3db557a4197f7b0cf92e1986b08fae6311"
},
"alpaca_gpt4_en": {
"file_name": "alpaca_gpt4_data_en.json",
"file_sha1": "647f4ad447bd993e4b6b6223d1be15208bab694a"
},
"alpaca_gpt4_zh": {
"file_name": "alpaca_gpt4_data_zh.json",
"file_sha1": "3eaa3bda364ccdd59925d7448a698256c31ef845"
},
"belle_0.5m": {
"hf_hub_url": "BelleGroup/train_0.5M_CN"
},
"belle_1m": {
"hf_hub_url": "BelleGroup/train_1M_CN"
},
"belle_2m": {
"hf_hub_url": "BelleGroup/train_2M_CN"
},
"belle_dialog": {
"hf_hub_url": "BelleGroup/generated_chat_0.4M"
},
"belle_math": {
"hf_hub_url": "BelleGroup/school_math_0.25M"
},
"belle_multiturn": {
"hf_hub_url": "BelleGroup/multiturn_chat_0.8M"
},
"guanaco": {
"hf_hub_url": "JosephusCheung/GuanacoDataset"
},
"firefly": {
"hf_hub_url": "YeungNLP/firefly-train-1.1M",
"columns": {
"prompt": "input",
"query": "",
"response": "target",
"history": ""
}
},
"codealpaca": {
"hf_hub_url": "sahil2801/CodeAlpaca-20k"
},
"alpaca_cot": {
"hf_hub_url": "QingyiSi/Alpaca-CoT"
},
"webqa": {
"hf_hub_url": "suolyer/webqa",
"columns": {
"prompt": "input",
"query": "",
"response": "output",
"history": ""
}
},
"ultra_chat": {
"script_url": "ultra_chat",
"columns": {
"prompt": "instruction",
"query": "",
"response": "output",
"history": "history"
}
},
"example": {
"script_url": "example_dataset",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
}
},
"comparison_gpt4_en": {
"file_name": "comparison_gpt4_data_en.json",
"file_sha1": "eeb295ce0ab011c37af52596460c8a57d07ad19f"
},
"comparison_gpt4_zh": {
"file_name": "comparison_gpt4_data_zh.json",
"file_sha1": "b99a41c1c864019d9b0c07dbcd5df0560cf33ce0"
},
"hh_rlhf_en": {
"script_url": "hh_rlhf_en",
"columns": {
"prompt": "instruction",
"query": "",
"response": "output",
"history": "history"
}
},
"wiki_demo": {
"file_name": "wiki_demo.txt",
"file_sha1": "b2288edb05b233e5b35250fd4b308a5fa21fa66d",
"columns": {
"prompt": "text",
"query": "",
"response": "",
"history": ""
}
},
"pretrain_data": {
"file_name": "pretrain_data",
"columns": {
"prompt": "content",
"query": "",
"response": "",
"history": ""
}
}
}