songlab-cal/tape
Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.
PythonBSD-3-Clause
Issues
- 0
- 0
support OMP_NUM_THREADS for CPU limit
#136 opened by alexweisberg - 0
Usability questions
#135 opened by dMedinaO - 1
wild type sequence for stability dataset
#131 opened by lzhangUT - 1
Data splits for stability task
#134 opened by agitter - 0
- 0
- 0
- 1
How to fine-tune a new task?
#128 opened by Binyun-Z - 5
- 1
babbler-1900 model doesnt work!
#123 opened by hkoohy - 1
the size of pre-train model 's input data
#127 opened by willow-yll - 2
attention masks tokenizer
#126 opened by Ch-rode - 2
cannot import tape
#124 opened by willow-yll - 2
Adding other metrics for validation steps
#125 opened by marcmk6 - 0
- 0
EOFError: Ran out of input
#121 opened by ZhengYang-00 - 0
Filtered Remote Homology Pretraining Dataset
#118 opened by cutecows - 0
about proteins emb
#120 opened by viko-3 - 0
About different length proteins
#119 opened by viko-3 - 2
Issue downloading weights
#117 opened by rmwu - 0
- 9
How to run with file in Gitlab
#114 opened by willow-yll - 0
Update version and pip package
#113 opened by rmrao - 2
Fine-Tune Downstream Tasks
#105 opened by yuanenming - 3
protein embedding is odd
#101 opened by jxzly - 9
some wrong with url of config.json
#112 opened by willow-yll - 11
about ProteinBertModel
#115 opened by viko-3 - 1
One-hot vocab
#109 opened by erika-alden - 4
Pfam dataset version and preprocess
#104 opened by apeterswu - 1
Positional embedding
#102 opened by linnlii - 2
- 2
Where can I download the training and testing for the GFP fluorescence task?
#99 opened by PraljakReps - 1
Typo in README file
#97 opened by simoncorrea - 1
- 4
OOM when calling pretrained models on sequences
#88 opened by wward97 - 1
- 1
Sequence to Sequence Bert Classification Model
#100 opened by markpb2-ai - 2
Creating new embedding with a portion of data
#94 opened by SukruHan - 1
- 1
- 1
Vocabulary used for Pre-Trained BERT Model
#90 opened by simolanzi - 2
- 2
can't start pretrain with --nproc_per_node > 1
#85 opened by FTD007 - 2
Mutli GPU takes 10 times longer than single GPU
#86 opened by donal1 - 5
cuda out of memory when increasing samplesize
#80 opened by kkpsiren - 1
- 1
Training LSTM language model on own data
#83 opened by kodrzywolek - 0
Question about ProteinNet dataset
#84 opened by akirasosa - 7
tape-eval vs. huggingface api?
#82 opened by hyeh20