salesforce/progen

Issues

• Could someone tell me about how to train models?

  #47 opened 9 months ago by maoke0603
  0

• CUDA Out of Memory Error When Running sample.py with a large --num-samples

  #45 opened 9 months ago by JoshPhd
  2

• Duplicate Sequences with Different runs

  #46 opened 9 months ago by jamesrgraham
  1

• Generate sequence based on natural one

  #18 opened 2 years ago by avivlazar
  3

• How to specify a control tag in the sample script?

  #15 opened 2 years ago by LiorZ
  3

• Control tags not in tokenizer

  #40 opened a year ago by lhallee
  1

• How progen handles sequences greater than 2048？

  #44 opened a year ago by wenyuhaokikika
  0

• Predicting model for CM and MDH dataset

  #31 opened 2 years ago by Tsinghua-gongjing
  2

• what is GB1 (top100avg) ?

  #43 opened a year ago by wenyuhaokikika
  0

• How to generate non-natural sequences of an interest protein using ProGen

  #28 opened 2 years ago by Eagan-lau
  1

• Fine Tuning the Model

  #21 opened 2 years ago by cv277
  9

• can somebody please give me the training code of progen2? i want to know how to train the model

  #42 opened a year ago by leobince
  0

• Are the tags of the training data avaliable? And where can i find it? Thanks

  #41 opened a year ago by leobince
  0

• How to generate sequences of a particular family using PROGEN2?

  #27 opened 2 years ago by Sireesiru
  2

• Releasing cleaned version of ProGen1?

  #30 opened 2 years ago by canallee
  1

• Could you please open source the dataset used for pre-training?

  #39 opened a year ago by Lyu6PosHao
  0

• Can't find the patch file named 'estimator.patch'

  #38 opened a year ago by 511515njlkh
  0

• Training details of discriminator

  #37 opened a year ago by Lifedecoder
  0

• URL from huggingface

  #35 opened a year ago by wkeymis
  0

• Lysozyme dataset needed

  #34 opened 2 years ago by SabBottazzi
  1

• Segmentation fault (core dumped)

  #32 opened 2 years ago by lvdongyuan
  0

• Client Error: Unauthorized for url

  #22 opened 2 years ago by AhmedKazlak
  1

• A question about "context"

  #26 opened 2 years ago by 1185307269
  1

• none

  #25 opened 2 years ago by xubocheng
  1

• I want to generate unnatural protein sequences from a gene family using Progen2

  #24 opened 2 years ago by Seaxingzhou
  1

• Weird behavior with memory usage within samply.py

  #10 opened 2 years ago by GrayWasTaken
  1

• It looks like the config file at './checkpoints/progen2-large' is not a valid JSON file.

  #23 opened 2 years ago by bj600800
  0

• Models difference

  #20 opened 2 years ago by Dongchengzhi
  0

• Runnable model

  #19 opened 2 years ago by okaris
  0

• Can one protect some fragments during generation

  #17 opened 2 years ago by data2code
  0

• How is the sequence ID calculated in an efficient manner

  #16 opened 2 years ago by eric-jm-lang
  1

• Is there a plan on packaging ProGen and its utilities on PyPI or something?

  #14 opened 2 years ago by martinez-zacharya
  0

• How to obtain Test-max90 and Test-max50?

  #13 opened 2 years ago by LGH1gh
  0

• Add a sequence classification head to ProtGen2

  #8 opened 2 years ago by franzigeiger
  2

• How can we extract embedding for a protein sequence?

  #12 opened 2 years ago by suresh-pokharel
  0

• RuntimeError

  #11 opened 2 years ago by ZeroKeng
  0

• Data for antibody set

  #9 opened 2 years ago by oliverdutton
  0

• correlation with Facebook ESM's log_likelihood

  #4 opened 3 years ago by avilella
  8

• how to run log likelihood score script on a 2 chain protein?

  #5 opened 2 years ago by avilella
  2

• Sampling conditional token distribution

  #7 opened 3 years ago by aiXander
  1

• Many repeats in Progen2 model predictions

  #1 opened 3 years ago by amirshane
  4

• Assertion error when running example code

  #2 opened 3 years ago by cyrusmaher
  3

• Error when running likelihood.py example for progen2-large on cpu

  #3 opened 3 years ago by cyrusmaher
  1