add ultrafeedback and fineweb #4085 #4132

Former-commit-id: 12d79f89c5
This commit is contained in:
hiyouga
2024-06-08 02:42:34 +08:00
parent de9e773764
commit 3547a26f86
4 changed files with 38 additions and 23 deletions

View File

@@ -391,6 +391,16 @@
"rejected": "rejected"
}
},
"ultrafeedback": {
"hf_hub_url": "llamafactory/ultrafeedback_binarized",
"ms_hub_url": "llamafactory/ultrafeedback_binarized",
"ranking": true,
"columns": {
"prompt": "instruction",
"chosen": "chosen",
"rejected": "rejected"
}
},
"orca_pairs": {
"hf_hub_url": "Intel/orca_dpo_pairs",
"ranking": true,
@@ -448,6 +458,15 @@
"assistant_tag": "assistant"
}
},
"ultrafeedback_kto": {
"hf_hub_url": "argilla/ultrafeedback-binarized-preferences-cleaned-kto",
"ms_hub_url": "AI-ModelScope/ultrafeedback-binarized-preferences-cleaned-kto",
"columns": {
"prompt": "prompt",
"response": "completion",
"kto_tag": "label"
}
},
"wiki_demo": {
"file_name": "wiki_demo.txt",
"columns": {
@@ -501,6 +520,18 @@
"prompt": "text"
}
},
"fileweb": {
"hf_hub_url": "HuggingFaceFW/fineweb",
"columns": {
"prompt": "text"
}
},
"fileweb_edu": {
"hf_hub_url": "HuggingFaceFW/fineweb-edu",
"columns": {
"prompt": "text"
}
},
"the_stack": {
"hf_hub_url": "bigcode/the-stack",
"ms_hub_url": "AI-ModelScope/the-stack",