Ber666/ToolkenGPT

Issues

• Incomplete evaluation script

  #26 opened 3 months ago by red-fox-yj
  0

• about the train data

  #25 opened 4 months ago by fghjdj
  0

• About the paper

  #24 opened 8 months ago by fghjdj
  1

• Can you provide the numerical ACC result on Kamel in Figure 2 of the paper?

  #23 opened 8 months ago by fairyshine
  2

• implement chatgpt+react and vicuna+react

  #17 opened 8 months ago by siyuyuan
  4

• Can you share the code using 0-shot Chatgpt?

  #20 opened 8 months ago by TreasureHunter
  3

• License

  #21 opened 8 months ago by jvhoffbauer
  2

• logits_bias

  #22 opened a year ago by lisaalaz
  1

• KeyError: '[PICKUP]'

  #18 opened a year ago by lisaalaz
  8

• A question about training data

  #19 opened a year ago by gao8319
  1

• ReAct in Table 2

  #16 opened a year ago by siyuyuan
  3

• How do you use ChatGPT+ReAcT?

  #15 opened a year ago by siyuyuan
  1

• kamel inference code

  #14 opened a year ago by lisaalaz
  1

• 64和96最大公约数是32

  #13 opened a year ago by dyabel
  1

• Unable to Reproduce FuncQA One-Hop Results

  #12 opened a year ago by chenhongqiao
  1

• Incorrect FuncQA Multi-Hop Ground Truth

  #11 opened a year ago by chenhongqiao
  1

• Missing template files in data

  #10 opened a year ago by sian-chen
  2

• Evaluation code for FuncQA

  #8 opened a year ago by sian-chen
  4

• Can you share the trained models?

  #6 opened a year ago by yonatanbitton
  2

• Missing KAMEL templates

  #7 opened a year ago by chenhongqiao
  3

• About dataset `FuncQA`

  #5 opened a year ago by yc1999
  2

• questions about training data

  #4 opened a year ago by ftgreat
  1

• Experiment environment

  #3 opened 2 years ago by passenger20
  2