ChatterjeeLab

/

PeptiVerse

like 0

Follow

Programmable Biology Group 113

Hi, thank you for the publication, very interesting work here! I wanted to try out a local installation of this repository and ran into a couple of issues. I have installed this model on AWS SageMaker AI with the Amazon Linux 2 operating system and on JupyterLab4 for the notebook. I am currently on an EC2 instance with the ml.g5.4xlarge node type that has 1 GPU. I was able to clone the repository and install the necessary packages in requirements.txt on a python 3.10 virtual environment. As this operating system's compiler is a bit old, I had to run mamba install -c conda-forge xgboost==3.1.2 instead of pip install xgboost for installation. I will post the two errors I encountered below. Did I do something wrong in my own usage of this repository, or is there something on your guy's end that should be fixed?

First, after installing all the requirements, I tried to run python inference.py as requested and got the following error message:

(PeptiVerse) [ec2-user@ip-172-21-244-78 PeptiVerse]$ python inference.py
tokenizer_config.json: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 95.0/95.0 [00:00<00:00, 996kB/s]
vocab.txt: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 93.0/93.0 [00:00<00:00, 1.07MB/s]
special_tokens_map.json: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 125/125 [00:00<00:00, 1.56MB/s]
config.json: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 724/724 [00:00<00:00, 8.98MB/s]
model.safetensors: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2.61G/2.61G [00:02<00:00, 1.08GB/s]
Traceback (most recent call last):
File "/home/ec2-user/SageMaker/fsx/Wu/PeptiVerse/inference.py", line 921, in
predictor = PeptiVersePredictor(
File "/home/ec2-user/SageMaker/fsx/Wu/PeptiVerse/inference.py", line 661, in init
self.smiles_embedder = SMILESEmbedder(self.device, clm_name=clm_name,
File "/home/ec2-user/SageMaker/fsx/Wu/PeptiVerse/inference.py", line 428, in init
self.tokenizer = SMILES_SPE_Tokenizer(vocab_path, splits_path)
File "/home/ec2-user/SageMaker/fsx/Wu/PeptiVerse/tokenizer/my_tokenizers.py", line 74, in init
raise ValueError("Can't find a vocabulary file at path '{}'.".format(vocab_file))
ValueError: Can't find a vocabulary file at path 'Classifier_Weight/tokenizer/new_vocab.txt'.
(PeptiVerse) [ec2-user@ip-172-21-244-78 PeptiVerse]$ python inference.py
Traceback (most recent call last):
File "/home/ec2-user/SageMaker/fsx/Wu/PeptiVerse/inference.py", line 921, in
predictor = PeptiVersePredictor(
File "/home/ec2-user/SageMaker/fsx/Wu/PeptiVerse/inference.py", line 661, in init
self.smiles_embedder = SMILESEmbedder(self.device, clm_name=clm_name,
File "/home/ec2-user/SageMaker/fsx/Wu/PeptiVerse/inference.py", line 428, in init
self.tokenizer = SMILES_SPE_Tokenizer(vocab_path, splits_path)
File "/home/ec2-user/SageMaker/fsx/Wu/PeptiVerse/tokenizer/my_tokenizers.py", line 74, in init
raise ValueError("Can't find a vocabulary file at path '{}'.".format(vocab_file))
ValueError: Can't find a vocabulary file at path 'Classifier_Weight/tokenizer/new_vocab.txt'.

I then tried to use the following script as specified:

from inference import PeptiVersePredictor

pred = PeptiVersePredictor(
manifest_path="best_models.txt", # best model list
classifier_weight_root=".", # repo root (where training_classifiers/ lives)
device="cuda", # or "cpu"
)

and got the following error message:

/home/ec2-user/anaconda3/envs/PeptiVerse/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
from .autonotebook import tqdm as notebook_tqdm
RoFormerForMaskedLM has generative capabilities, as prepare_inputs_for_generation is explicitly overwritten. However, it doesn't directly inherit from GenerationMixin. From 👉v4.50👈 onwards, PreTrainedModel will NOT inherit from GenerationMixin, and this model will lose the ability to call generate and other related functions.
- If you're using trust_remote_code=True, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
- If you are the owner of the model architecture code, please modify your model class such that it inherits from GenerationMixin (after PreTrainedModel, otherwise you'll get an exception).
- If you are not the owner of the model architecture class, please contact the model code owner to update it.

KeyError Traceback (most recent call last)
Cell In[1], line 3
1 from inference import PeptiVersePredictor
----> 3 pred = PeptiVersePredictor(
4 manifest_path="best_models.txt", # best model list
5 classifier_weight_root=".", # repo root (where training_classifiers/ lives)
6 device="cuda", # or "cpu"
7 )

File ~/SageMaker/fsx/Wu/PeptiVerse/inference.py:668, in PeptiVersePredictor.init(self, manifest_path, classifier_weight_root, esm_name, clm_name, smiles_vocab, smiles_splits, device)
665 self.models: Dict[Tuple[str, str], Any] = {}
666 self.meta: Dict[Tuple[str, str], Dict[str, Any]] = {}
--> 668 self._load_all_best_models()

File ~/SageMaker/fsx/Wu/PeptiVerse/inference.py:734, in PeptiVersePredictor._load_all_best_models(self)
731 continue
733 model_dir = self._resolve_dir(prop_key, m, mode)
--> 734 kind, obj, art = load_artifact(model_dir, self.device)
736 if kind in {"xgb", "joblib"}:
737 self.models[(prop_key, mode)] = obj

File ~/SageMaker/fsx/Wu/PeptiVerse/inference.py:146, in load_artifact(model_dir, device)
143 return "xgb", booster, art
145 if art.suffix == ".joblib":
--> 146 obj = joblib.load(art)
147 return "joblib", obj, art
149 if art.suffix == ".pt":

File ~/anaconda3/envs/PeptiVerse/lib/python3.10/site-packages/joblib/numpy_pickle.py:749, in load(filename, mmap_mode, ensure_native_byte_order)
744 return load_compatibility(fobj)
746 # A memory-mapped array has to be mapped with the endianness
747 # it has been written with. Other arrays are coerced to the
748 # native endianness of the host system.
--> 749 obj = _unpickle(
750 fobj,
751 ensure_native_byte_order=ensure_native_byte_order,
752 filename=filename,
753 mmap_mode=validated_mmap_mode,
754 )
756 return obj

File ~/anaconda3/envs/PeptiVerse/lib/python3.10/site-packages/joblib/numpy_pickle.py:626, in _unpickle(fobj, ensure_native_byte_order, filename, mmap_mode)
624 obj = None
625 try:
--> 626 obj = unpickler.load()
627 if unpickler.compat_mode:
628 warnings.warn(
629 "The file '%s' has been generated with a "
630 "joblib version less than 0.10. "
(...)
633 stacklevel=3,
634 )

File ~/anaconda3/envs/PeptiVerse/lib/python3.10/pickle.py:1213, in _Unpickler.load(self)
1211 raise EOFError
1212 assert isinstance(key, bytes_types)
-> 1213 dispatchkey[0]
1214 except _Stop as stopinst:
1215 return stopinst.value

KeyError: 118