423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-02 03:32:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add Magpie and Webinstruct dataset samples

Browse Source 
Adds two dataset samples claimed superior performance: Magpie (from Allen AI) and Webinstruct (from TIGER-Lab).

Former-commit-id: 74e49cca957d0bacd2c1d688e995a7370bef69f7
This commit is contained in:
Eli Costa 2024-06-15 19:31:56 -03:00 committed by GitHub
parent 06bbc29614
commit 6bbb8b4cd8
1 changed files with 23 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
data/dataset_info.json
View File

@ -524,13 +524,13 @@
"prompt": "text"
}
},
"fileweb": {
"fineweb": {
"hf_hub_url": "HuggingFaceFW/fineweb",
"columns": {
"prompt": "text"
}
},
"fileweb_edu": {
"fineweb_edu": {
"hf_hub_url": "HuggingFaceFW/fineweb-edu",
"columns": {
"prompt": "text"
@ -550,5 +550,25 @@
"prompt": "content"
},
"folder": "python"
},
"Magpie-Pro-300K-Filtered": {
"hf_hub_url": "Magpie-Align/Magpie-Pro-300K-Filtered",
"columns": {
"messages": "conversations"
},
"tags": {
"role_tag": "from",
"content_tag": "value",
"user_tag": "human",
"assistant_tag": "gpt"
},
"formatting": "sharegpt"
},
"WebInstructSub": {
"hf_hub_url": "TIGER-Lab/WebInstructSub",
"columns": {
"prompt": "question",
"response": "answer"
}
}
}