Muennighoff/sgpt

Issues

• Need help fine-tuning sgpt model

  #18 opened 3 months ago by faicalbounedjar
  9

• S-GPT

  #48 opened 3 months ago by Davidtverd
  0

• Usage for semantic search

  #47 opened 3 months ago by rut00
  6

• Can we switch Casual attention to Self attention for SGPT?

  #46 opened 4 months ago by ashokrajab
  2

• Usage for text-2-text-generation

  #45 opened 6 months ago by shafkat-07
  1

• Could I fine tune this model for Chinese datasets?

  #41 opened 9 months ago by asenasen123
  11

• HuggingFace script and Sentence Transformers script giving different results

  #44 opened 7 months ago by vladkvit
  2

• Could I change the max_seq_length?

  #43 opened 8 months ago by asenasen123
  3

• Fine-tune Muennighoff/SGPT-2.7B-weightedmean-msmarco-specb-bitfit using TSDAE approach

  #42 opened 8 months ago by BalajiAJ
  4

• Error when using sentence_transformer

  #14 opened a year ago by TamHHM
  15

• If I input more than the max_seq_length？

  #40 opened 10 months ago by runwean
  4

• How to fine tune on my datasets

  #2 opened 2 years ago by shaileshj2803
  8

• Why use low chunksizes?

  #39 opened a year ago by aksj98
  3

• Training scripts have wrong name of gpt-neo-125m

  #38 opened a year ago by aksj98
  2

• Have you tried different prompts in bi-encode model

  #36 opened a year ago by ttjjlw
  1

• does it support Korea and Japanese?

  #35 opened a year ago by sz2three
  1

• What is the principle and intuition of unsupervised embedding of SGPT?

  #33 opened a year ago by guotong1988
  1

• What is the core code of unsupervised embedding of SGPT?

  #34 opened a year ago by guotong1988
  2

• fine-tune sgpt-bloom-7b1-msmarco oom

  #32 opened a year ago by wing7171
  1

• Can I use multi GPUS

  #31 opened a year ago by magicleo
  2

• accelerate + deepspeed?

  #30 opened a year ago by alex-ht
  2

• the example model of 'SGPT-125M-weightedmean-nli-bitfit' not compatible with ST

  #29 opened a year ago by dengwx2009
  3

• When I train an encoder using bloom 3b, I get this error? What is the cause of this problem, please?

  #27 opened a year ago by ScottishFold007
  9

• Model taken down?

  #28 opened a year ago by extradosages
  5

• Training on unlabeled data (German)

  #26 opened a year ago by anastasiia-ps
  1

• chinese support?

  #25 opened a year ago by Lukangkang123
  4

• Asymmetric search models with longer max seq length?

  #23 opened a year ago by regstuff
  7

• Possible to quantize into 4-bit and 8-bit and still use the models

  #24 opened a year ago by regstuff
  1

• Fine Tuning

  #21 opened a year ago by Kartali-Mohamed
  0

• Use SGPT

  #20 opened a year ago by Kartali-Mohamed
  2

• Different model sizes

  #19 opened a year ago by KnutJaegersberg
  6

• Multilingual BLOOM SGPT max_seq_length is the max_length of text input?

  #17 opened a year ago by ennioferreirab
  2

• cannot reproduce leaderboard result

  #16 opened a year ago by hsl89
  1

• Evaluating cross encoders

  #15 opened a year ago by loopdeloop76
  2

• ValueError: not enough values to unpack (expected 2, got 1)

  #13 opened a year ago by Roopesh-Bharatwaj-K-R
  1

• Construct SGPT

  #11 opened 2 years ago by tsamarahrana
  4

• Metric scores for CQADupStack

  #10 opened 2 years ago by rafaljanwojcik
  2

• Theory question about the token weightings for symetric search.

  #9 opened 2 years ago by cm2435
  2

• Learning rate & schedule

  #7 opened 2 years ago by malteos
  2

• Training SGPT for Custom Dataset

  #6 opened 2 years ago by rajarajanvakil
  1

• OpenAI-GPT3 search endpoint deprecated

  #5 opened 2 years ago by rajarajanvakil
  4

• generating similar sentences

  #4 opened 2 years ago by nikky4D
  1