hkust-nlp/deita

Issues

• Could you please publish the original data pool?

  #27 opened a month ago by ShadowTinker
  2

• The length of samples

  #26 opened a month ago by Ber666
  1

• If I want to use vllm, which version should I install

  #25 opened 2 months ago by kissshhot
  0

• Does the EVOL process of instruction dataset has been released?

  #24 opened 2 months ago by dsj96
  0

• reproduce mt-bench score

  #23 opened 3 months ago by bpucla
  1

• Questions about performance improvement in Open LLM leaderboard

  #21 opened 3 months ago by minstar
  3

• Questions about the "Pool=50K" in your paper.

  #12 opened 3 months ago by DLiquor
  2

• [Question] Regarding the order bias in sample scoring.

  #15 opened 3 months ago by liujuncn
  2

• Question about which score to ultimately use for the filtering process.

  #19 opened 3 months ago by 447428054
  2

• Have you conducted ablation experiments with three factors: Complexity, Quality, and Diversity? Which one has the greatest impact on performance improvement?

  #22 opened 3 months ago by 447428054
  1

• Scorer models on hub are 7b not 13b

  #18 opened 4 months ago by edbeeching
  2

• Cosine distance computation

  #20 opened 3 months ago by sangkeun00
  4

• How did you train the complexity & quality scorer

  #3 opened 5 months ago by philschmid
  8

• Can we support more languages?

  #16 opened 4 months ago by zhangfan-algo
  1

• [Question] Script to train Scorer model?

  #11 opened 4 months ago by agi-piggy
  1

• What content is encoded when Llama13B encoded a sentence

  #8 opened 5 months ago by cgpeter96
  3

• [question]Did you use the mean value of all token embedding in repr filter?

  #10 opened 5 months ago by Force1ess
  3

• request: is code of "Repr Filter" can be open source too?

  #2 opened 5 months ago by Force1ess
  4

• [question] repr_filter encoding only the instruction or instruction and anwser?

  #9 opened 5 months ago by Force1ess
  1

• [Question] Is the 6k dataset is a subset of 10k dataset.

  #7 opened 5 months ago by ChenMnZ
  1

• Some questions about running the scorer for arbitary model

  #5 opened 5 months ago by HelloWorldLTY
  2

• data of deita's dpo+sft

  #4 opened 5 months ago by jiezhangGt
  0