关于测评结果

[1264561652]

readme里的测评结果还可以提高吗？

[shibing624]

可以，更高质量的数据和模型，效果更好

[1264561652]

我的意思是能在你的这个代码上改的结果更高吗？如果能的话应该在哪些部分进行更改才可能使效果提高明显

---- 回复的原邮件 ---- | 发件人 | Ming Xu @.> | | 日期 | 2023年05月25日 17:30 | | 收件人 | @.> | | 抄送至 | @.>@.> | | 主题 | Re: [shibing624/text2vec] 关于测评结果 (Issue #69) |

可以，更高质量的数据和模型，效果更好

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

[shibing624]

我没刻意去刷评估数据的效果；你可以自己调参试试。

top_p=0.9,
#Moderately increase the probability threshold of nucleus sampling to increase the quantity of candidate tokens and increase generation diversity.

temperature=1.0,
#The previous low temperature parameter could lead to a severe polarization in the probability distribution of generated words, which degenerates the generation strategy into greedy decoding.

do_sample=True,
#do_sample parameter is set to False by default. After setting to True, the generation methods turn into beam-search multinomial sampling decoding strategy.

no_repeat_ngram_size=6,
#Configure the probability of the next repeating n-gram to 0, to ensure that there are no n-grams appearing twice. This setting is an empirical preliminary exploration.

repetition_penalty=1.8,
#For words that have appeared before, in the subsequent prediction process, we reduce the probability of their reoccurrence by introducing the repetition_penalty parameter. This setting is an empirical preliminary exploration.

[1264561652]

好的，谢谢

---- 回复的原邮件 ---- | 发件人 | Ming Xu @.> | | 日期 | 2023年05月25日 17:43 | | 收件人 | @.> | | 抄送至 | @.>@.> | | 主题 | Re: [shibing624/text2vec] 关于测评结果 (Issue #69) |

我没刻意去刷评估数据的效果；你可以自己调参试试。

top_p=0.9, #Moderately increase the probability threshold of nucleus sampling to increase the quantity of candidate tokens and increase generation diversity.

temperature=1.0, #The previous low temperature parameter could lead to a severe polarization in the probability distribution of generated words, which degenerates the generation strategy into greedy decoding.

do_sample=True, #do_sample parameter is set to False by default. After setting to True, the generation methods turn into beam-search multinomial sampling decoding strategy.

no_repeat_ngram_size=6, #Configure the probability of the next repeating n-gram to 0, to ensure that there are no n-grams appearing twice. This setting is an empirical preliminary exploration.

repetition_penalty=1.8, #For words that have appeared before, in the subsequent prediction process, we reduce the probability of their reoccurrence by introducing the repetition_penalty parameter. This setting is an empirical preliminary exploration.

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.(由于长期不活动，机器人自动关闭此问题，如果需要欢迎提问)