EmoLLM评测

April 9, 2024 · View on GitHub

通用指标评测

ModelROUGE-1ROUGE-2ROUGE-LBLEU-1BLEU-2BLEU-3BLEU-4
Qwen1_5-0_5B-chat27.23%8.55%17.05%26.65%13.11%7.19%4.05%
InternLM2_7B_chat_qlora37.86%15.23%24.34%39.71%22.66%14.26%9.21%
InternLM2_7B_chat_full32.45%10.82%20.17%30.48%15.67%8.84%5.02%
InternLM2_7B_base_qlora_5epoch41.94%20.21%29.67%42.98%27.07%19.33%14.62%
InternLM2_7B_base_qlora_10epoch43.47%22.06%31.4%44.81%29.15%21.44%16.72%

专业指标评测

ModelComprehensivenessProfessionalismAuthenticitySafety
InternLM2_7B_chat_qlora1.322.202.101.00
InternLM2_7B_chat_full1.402.452.241.00
InternLM2_20B_chat_lora1.422.392.221.00