ColossalAI/applications/Chat/evaluate/config/config_cn.json

128 lines
2.1 KiB
JSON

{
"language": "cn",
"category": {
"brainstorming": {
"GPT": [
"language organization",
"relevance",
"creativity",
"practicality",
"reasonableness"
],
"Metrics": [
"Distinct"
]
},
"chat": {
"GPT": [
"language organization",
"relevance",
"naturalness",
"engagingness",
"reasonableness"
],
"Metrics": [
"Distinct"
]
},
"classification": {
"GPT": [
"language organization",
"relevance",
"correctness"
],
"Metrics": [
"Precision",
"Recall",
"F1 score",
"CHRF"
]
},
"closed_qa": {
"GPT": [
"language organization",
"relevance",
"correctness"
],
"Metrics": [
"BLEU",
"ROUGE",
"BERTScore",
"CHRF"
]
},
"extraction": {
"GPT": [
"language organization",
"relevance",
"correctness"
],
"Metrics": [
"Precision",
"Recall",
"F1 score",
"CHRF"
]
},
"generation": {
"GPT": [
"language organization",
"relevance",
"diversity"
],
"Metrics": [
"BLEU",
"ROUGE",
"BERTScore"
]
},
"open_qa": {
"GPT": [
"language organization",
"relevance",
"correctness"
],
"Metrics": [
"Distinct"
]
},
"rewriting": {
"GPT": [
"language organization",
"relevance",
"correctness"
],
"Metrics": [
"BLEU",
"ROUGE",
"BERTScore"
]
},
"roleplay": {
"GPT": [
"language organization",
"relevance",
"fidelity",
"creativity"
],
"Metrics": [
"Distinct"
]
},
"summarization": {
"GPT": [
"language organization",
"relevance",
"correctness",
"conciseness"
],
"Metrics": [
"BLEU",
"ROUGE",
"BERTScore",
"CHRF"
]
}
}
}