67 questions
0
votes
1
answer
52
views
Generating partial string as output after fine-tuning T5 model
I'm using fine-tuned T5 model for performing spell checks in my dataset of consisting of reviews. However, I'm facing an issue where the model when performing spell checks does not give entire string ...
0
votes
1
answer
35
views
Why my nlp model reload many times when processing question?
After receiving question, my program calls the run_predict function then finds the best paragraph match with the question.
After that, my model is constantly reloaded without knowing the reasons.
from ...
0
votes
1
answer
134
views
Simple transformers ConvAI Model completely freezes and crashes PC. Two different problems on two different machines
I am trying to load and train a ConvAI Model, fairly new to the whole concept. Keep running into two main problems - one on my personal computer, one on a corporate machine.
On my personal machine, it ...
- 3
0
votes
1
answer
65
views
Use of Params in pyspak
In this example, I am trying to use overrides as a Params object and I want it to be used as a list of strings.
But I am not able to assign its value using the below code.
class _AB(Params):
...
- 323
-1
votes
2
answers
361
views
simpletransforers use_cuda=True not working
wanted to try CUDA (I have an RTX 3070 TI) on my Windows setup, using this code:
import pandas as pd
from simpletransformers.classification import ClassificationModel
from sklearn.model_selection ...
- 37
1
vote
0
answers
443
views
How to do you load a model from a checkpoint using simple transformers?
I am using the simple transformers library, I have just finished training a model and now I want to load it to try making some predictions. However, I must be doing something wrong because it keeps ...
- 163
3
votes
0
answers
977
views
Using .generate function for beam search over predictions in custom model extending TFPreTrainedModel class
I want to use .generate() functionality of hugging face in my model's predictions.
My model is a custom model inehriting from "TFPreTrainedModel" class and has a custom transformer ...
- 41
1
vote
0
answers
40
views
SimpleTransformers 'Roberta' problem with token recognition
I have a problem while predicting the labels in a token sequence with a SimpleTransformers model trained previously.
When I predict the labels in a sequence, the model omits lots of tokens, depending ...
-2
votes
1
answer
173
views
I can run the model which I made with simpletransformers in google colab, but when I run it in spyder or visual studio, it gives an error
from simpletransformers.classification import ClassificationModel
import torch
Bert_model = ClassificationModel(
"bert", "bert_model")
a=Bert_model.predict(["kötü"])
...
-4
votes
1
answer
213
views
Error when pip installing simpletransformers
I am trying to install simpletransformers via pip, but it gives me the following error:
"ERROR: Exception:
Traceback (most recent call last):
File "/sw/arch/Debian10/EB_production/2021/...
0
votes
1
answer
658
views
Simpletransformers always generating empty strings
so i was trying to train a chatbot using transformers for my ai assistant , i thought simpletransformer package in python would help me speed up alot of my tasks . I soon gathered a good dataset over ...
- 144
2
votes
1
answer
754
views
Simple Transformers producing nothing?
I have a simple transformers script looking like this.
from simpletransformers.seq2seq import Seq2SeqModel, Seq2SeqArgs
args = Seq2SeqArgs()
args.num_train_epoch=5
model = Seq2SeqModel(
"...
- 121
0
votes
0
answers
721
views
I get this error when i try importing simple transformers
import logging
from simpletransformers.question_answering import QuestionAnsweringModel, QuestionAnsweringArgs
i run the above piece of code and get this error
> ModuleNotFoundError ...
1
vote
1
answer
396
views
SimpleTransformers model not training on whole data (As shown in brackets under epochs bar)?
My data has 1751 sentences however when training a number appears under the epochs bars. Sometimes it is 1751 which makes sense it's the number of sentences I have, but most of the times it's 50% the ...
- 730
0
votes
1
answer
242
views
Loading pool layer of simple transformer
I have a fine tuned simple transformer representation model. Now I want to save the weights of only the pool layer in pickle format and put it in the pool layer of another custom auto encoder that I ...
1
vote
0
answers
181
views
Simpletransformers not using all data to train and evaluate?
so I am using simpletransformers on my classification task, I have 2 columns in my Dataframe (sentence, label) of size 3890
When I train the model it shows that it is only using 8 samples from my ...
- 730
0
votes
1
answer
1k
views
using gpu with simple transformer mt5 training
mt5 fine-tuning does not use gpu(volatile gpu utill 0%)
Hi, im trying to fine tuning for ko-en translation with mt5-base model.
I think the Cuda setting was done correctly(cuda available is True)
But ...
- 31
2
votes
0
answers
1k
views
Adding 'decoder_start_token_id' with SimpleTransformers
Training MBART in Seq2Seq with SimpleTransformers but getting an error I am not seeing with BART:
TypeError: shift_tokens_right() missing 1 required positional argument: 'decoder_start_token_id'
So ...
- 389
0
votes
1
answer
2k
views
FME issue, deleting row based cell value
Hell all, so let try to describe my problem in the best light possible. I have experience with Python but have never used FME. I would like to delete a full row of data based on criteria in a ...
- 21
4
votes
2
answers
13k
views
unable to mmap 1024 bytes - Cannot allocate memory - even though there is more than enough ram
I'm currently working on a seminar paper on nlp, summarization of sourcecode function documentation. I've therefore created my own dataset with ca. 64000 samples (37453 is the size of the training ...
- 105
1
vote
1
answer
126
views
Set disjoint labels for Multi-Label classification with Simpletransformers
I need to clasify some text in labels of emotions. I'm using Multi-Label Classification because the same text can contain more than one emotion, but I want to implement that some of them be disjoint ...
- 1,817
1
vote
1
answer
718
views
Not able to use NERModel due to import issue from SimpleTransformers
I'm trying to use SimpleTransformers module for this competition.
After successfully installing the package SimpleTransformers in kernel , i'm trying to import NERModel and NERArgs packages from ...
- 11
2
votes
0
answers
1k
views
"PanicException: no entry found for key" error running simpletransformers on Google Colab
I encountered this error while running simpletransformers on Google Colab. I enabled h/w accelerator as GPU and ran the code.
from simpletransformers.classification import ClassificationModel
# Create ...
- 1,076
8
votes
1
answer
662
views
Error while loading fine-tuned simpletransformer model in Docker Container
I am saving and loading a model using torch.save() and torch.load() commands.
While loading a fine-tuned simple transformer model in Docker Container, I am facing this error which I am not able to ...
- 163
3
votes
1
answer
5k
views
How to get top generated text of T5 transformers?
I trained a T5 transformer using simpletransformers library.
Here is a code to get the predictions:
pred_values = model.predict(input_values)
However, it just returns the top or greedy prediction, ...
- 9,816