chen700564/RGB

Issues

• ./evalue.py中fact_label的0和1是不是反了？

  #22 opened 2 months ago by PPMark0712
  1

• 您好，我在评估时发现模型在en_refine和zh_refine的性能远高于原来en和zh上的性能，请问是改动了很多答案吗

  #21 opened 4 months ago by kkkeepgoing
  2

• 在评测信息整合能力时，noise_rate这个参数没有用到？

  #20 opened 6 months ago by Jianwei-Lv
  2

• how to load the dataset to RAG, which part are docs? the content in "positive" or something?

  #19 opened 6 months ago by yxm0513
  1

• 关于预测结果的字段含义

  #18 opened 7 months ago by lwj2001
  1

• 您好，您的评估支持使用vllm部署的开源模型吗

  #17 opened 7 months ago by lwj2001
  2

• There are too many errors in the dataset！

  #12 opened 8 months ago by CalmCapK
  8

• data path given in fact_evalue and reject_evalue is incorrect.

  #16 opened 7 months ago by scarydemon2
  1

• 评价材料的问题

  #15 opened 8 months ago by qianzhang2018
  0

• License of use.

  #14 opened 8 months ago by MatheusHRV
  2

• How are the noise_rate and correct_rate parameters set for this table?

  #13 opened 8 months ago by Gera001
  1

• Welcome to join OpenCompass

  #10 opened 9 months ago by tonysy
  2

• Rejection Rate Evaluation Issue

  #9 opened 9 months ago by jhshen95
  4

• Data construction

  #11 opened 9 months ago by lqcStar
  0

• Some issues trying Rejection Rate

  #8 opened 9 months ago by alvelvis
  4

• How you create the data

  #7 opened 10 months ago by Linda230
  2

• Unable to reproduce Counterfactual Robustness result with ChatGPT

  #6 opened 10 months ago by baichuan-assistant
  5

• confused by the calculation of accuracy

  #5 opened 10 months ago by wzp21142
  6

• rejection rate of chatGPT

  #3 opened a year ago by valdesguefa
  8

• RAG's future

  #4 opened a year ago by valdesguefa
  1

• Error during the evaluation of model

  #2 opened a year ago by valdesguefa
  1

• Need openAI key for evaluating LLM?

  #1 opened a year ago by valdesguefa
  1