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 datasets

Browse Source 
Former-commit-id: 02e4b47dea1b25905c61f2ace88bab112610f021
This commit is contained in:
hiyouga
2023-07-19 20:59:15 +08:00
parent 6bc585e4be
commit e9de1951dd
12 changed files with 107 additions and 134 deletions
Download Patch File Download Diff File Expand all files Collapse all files

101
data/dataset_info.json
View File

@@ -1,6 +1,7 @@
{
"alpaca_en": {
"hf_hub_url": "tatsu-lab/alpaca"
"file_name": "alpaca_data_en_52k.json",
"file_sha1": "607f94a7f581341e59685aef32f531095232cf23"
},
"alpaca_zh": {
"file_name": "alpaca_data_zh_51k.json",
@@ -14,6 +15,72 @@
"file_name": "alpaca_gpt4_data_zh.json",
"file_sha1": "3eaa3bda364ccdd59925d7448a698256c31ef845"
},
"self_cognition": {
"file_name": "self_cognition.json",
"file_sha1": "6287a730ada924fc5d9eadc6d8f865e01b7a6f67"
},
"oaast_sft": {
"file_name": "oaast_sft.json",
"file_sha1": "08912e34fb165db137d3436db4c35321e33b28d1",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
}
},
"oaast_sft_zh": {
"file_name": "oaast_sft_zh.json",
"file_sha1": "e0a2e7e8eff355434ada6c9b7f70bb915f941dd4",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
}
},
"sharegpt_zh": {
"file_name": "sharegpt_zh_27k.json",
"file_sha1": "baf766bcf3d61f1b783728c14ce695af57a86e6e",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
}
},
"refgpt_zh_p1": {
"file_name": "refgpt_zh_50k_p1.json",
"file_sha1": "995043a909eed6693f850a96fccb4d3803f3ea5e",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
}
},
"refgpt_zh_p2": {
"file_name": "refgpt_zh_50k_p2.json",
"file_sha1": "d9442d5c4541fe5489b5b571871fbe7595ee3809",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
}
},
"example": {
"script_url": "example_dataset",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
}
},
"guanaco": {
"hf_hub_url": "JosephusCheung/GuanacoDataset"
},
"belle_0.5m": {
"hf_hub_url": "BelleGroup/train_0.5M_CN"
},
@@ -38,9 +105,6 @@
"history": "history"
}
},
"guanaco": {
"hf_hub_url": "JosephusCheung/GuanacoDataset"
},
"firefly": {
"hf_hub_url": "YeungNLP/firefly-train-1.1M",
"columns": {
@@ -74,38 +138,9 @@
"history": "history"
}
},
"oaast_sft": {
"file_name": "oaast_sft.json",
"file_sha1": "08912e34fb165db137d3436db4c35321e33b28d1",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
}
},
"oaast_sft_zh": {
"file_name": "oaast_sft_zh.json",
"file_sha1": "e0a2e7e8eff355434ada6c9b7f70bb915f941dd4",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
}
},
"novel_tokens512_50k": {
"hf_hub_url": "zxbsmk/webnovel_cn"
},
"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": "96fa18313544e22444fe20eead7754b17da452ae"