Error when running Parser about lambeq

[Thommy257]

Hi,
thanks for submitting this issue, this has happened before and we are currently investigate it. Could you please give us the following information about your system:

• Which python version do you use?
• Do you use anaconda?
• Which IDE do you use?
• Are you running your code in a notebook/ ipython shell?

In the meantime, you can download the model through this link, extract it, and pass the path to the extracted files to the BobcatParser:

from lambeq import BobcatParser

parser = BobcatParser(model='path/to/model')
diagram = parser.sentence2diagram('This is a test sentence')
diagram.draw()

[Stephenito]

I have the same problem with SSL certificate. I have tried with the following configuration:

• Python version 3.8
• Not using Anaconda
• Jupyter-lab on browser (tried with both Opera GX and Google Chrome) with a notebook
• I tried even with the Python Shell, still doesn't work.

I also downloaded the model from the link you provided and extracted it. I copy-pasted your code, and tried as paths the relative paths and abosulte paths (I/O is working properly with other files) of both the directory containing the model and the file 'pytorch_model.bin', but still the program returns the same SSL error.

Is there something i am doing wrong while loading the local file? Thanks for your help.

[Thommy257]

Sorry, the download link might have been deprecated. Can you try downloading the model from https://qnlp.cambridgequantum.com/models/bert/latest/model.tar.gz?

Also, I realised that the correct variable is model_name_or_path. So this will work:

from lambeq import BobcatParser

parser = BobcatParser(model_name_or_path='path/to/model')
diagram = parser.sentence2diagram('This is a test sentence')
diagram.draw()

Many apologies!

Update: the link was broken.

[ACE07-Sev]

I downloaded the model.tar.gz. How shall I set the Parser path to it? I'm not very familiar with .tar.gz files.

[Thommy257]

Hi @ACE07-Sev, .tar.gz is an compressed file. You need to extract it first. Maybe this page helps: https://superuser.com/questions/215629/how-to-open-a-tar-gz-file-in-windows

[ACE07-Sev]

Hi yes now it's fixed. I extracted it and then addressed the file path to that. thank you so much

[ACE07-Sev]

Hi sorry, I ran the model and got this error :

2022-06-06 18:03:29.258323: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2022-06-06 18:03:29.259328: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
Traceback (most recent call last):
File "C:\Users\elmm\Desktop\CQM\QNLP Depression.py", line 104, in
trainer.fit(train_dataset, val_dataset, logging_step=12)
File "C:\Users\elmm\AppData\Local\Programs\Python\Python39\lib\site-packages\lambeq\training\trainer.py", line 365, in fit
y_hat, loss = self.training_step(batch)
File "C:\Users\elmm\AppData\Local\Programs\Python\Python39\lib\site-packages\lambeq\training\quantum_trainer.py", line 149, in training_step
y_hat, loss = self.optimizer.backward(batch)
File "C:\Users\elmm\AppData\Local\Programs\Python\Python39\lib\site-packages\lambeq\training\spsa_optimizer.py", line 125, in backward
y0 = self.model(diagrams)
File "C:\Users\elmm\AppData\Local\Programs\Python\Python39\lib\site-packages\lambeq\training\model.py", line 59, in call
return self.forward(*args, **kwds)
File "C:\Users\elmm\AppData\Local\Programs\Python\Python39\lib\site-packages\lambeq\training\tket_model.py", line 131, in forward
return self.get_diagram_output(x)
File "C:\Users\elmm\AppData\Local\Programs\Python\Python39\lib\site-packages\lambeq\training\tket_model.py", line 103, in get_diagram_output
seed=self._randint()
File "C:\Users\elmm\AppData\Local\Programs\Python\Python39\lib\site-packages\lambeq\training\tket_model.py", line 71, in _randint
return np.random.randint(low, high)
File "mtrand.pyx", line 746, in numpy.random.mtrand.RandomState.randint
File "_bounded_integers.pyx", line 1334, in numpy.random._bounded_integers._rand_int32
ValueError: low is out of bounds for int32

The parser is working now so I think besides this we can close the issue.

[ACE07-Sev]

I tried changing the seed to 7 for instance but still got the error. May I ask how can I resolve this?

[Thommy257]

Follow-up in #12