# Model Inference API error
**URL:**
**Author:**  [@dilolo](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdilolo)%5C
**Post date:** [May 5, 2024, 2:00pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-inference-api-error%2F85265%2F1 "2024-05-05T14:00:53Z")
Hi
I used XLM-RoBERTa for fine tuning this model to determine the text language. After training, I uploaded the model to the huggingface repository. When trying to use the Inference API on a model page for a model test I get an error
Can’t load tokenizer using from\_pretrained, please update its configuration: data did not match any variant of untagged enum PyPreTokenizerTypeWrapper at line 83 column 3
```auto
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('xlm-roberta-base')
def tokenize_function(examples):
return tokenizer(examples['text'], padding="max_length", truncation=True, max_length=128)
# Apply tokenization to each split
dataset = dataset.map(tokenize_function, batched=True)
from transformers import AutoModelForSequenceClassification
model = AutoModelForSequenceClassification.from_pretrained('xlm-roberta-base', num_labels=21)
from transformers import Trainer, TrainingArguments
from sklearn.metrics import accuracy_score, precision_recall_fscore_support
import numpy as np
def compute_metrics(pred):
labels = pred.label_ids
preds = pred.predictions.argmax(-1)
precision, recall, f1, _ = precision_recall_fscore_support(labels, preds, average='weighted')
acc = accuracy_score(labels, preds)
return {
'accuracy': acc,
'f1': f1,
'precision': precision,
'recall': recall
}
training_args = TrainingArguments(
output_dir='./results',
num_train_epochs=3,
per_device_train_batch_size=16,
per_device_eval_batch_size=64,
warmup_steps=500,
weight_decay=0.01,
logging_dir='./logs',
logging_steps=10,
evaluation_strategy="epoch",
save_strategy="epoch"
)
trainer = Trainer(
model=model,
args=training_args,
train_dataset=dataset['train'],
eval_dataset=dataset['validation'],
compute_metrics=compute_metrics
)
trainer.train()
from huggingface_hub import notebook_login
notebook_login()
repo_name = "my_repo"
model.push_to_hub(repo_name)
tokenizer.push_to_hub(repo_name)
```
Why could this be?
---
**Author:**  [@nielsr](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fnielsr)%5C
**Post date:** [May 6, 2024, 9:02am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-inference-api-error%2F85265%2F2 "2024-05-06T09:02:12Z")
Thanks for reporting, will ping the team.
Looks like the same issue as [Can't load tokenizer using from\_pretrained, Inference API](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcant-load-tokenizer-using-from-pretrained-inference-api%2F85235)
---
**Author:**  [@asif00](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fasif00)%5C
**Post date:** [May 6, 2024, 2:03pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-inference-api-error%2F85265%2F3 "2024-05-06T14:03:59Z")
I am also facing the same issue. It still doesn’t work on Model’s default Inference API but I could make it work with MBart50Tokenizer on HF space. Here is the [Space](https://huggingface.co/spaces/asif00/Bengali_Sentence_Error_Correction__mbart_bn_error_correction) I was testing it.
---
**Author:**  [@dilolo](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdilolo)%5C
**Post date:** [May 6, 2024, 3:02pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-inference-api-error%2F85265%2F4 "2024-05-06T15:02:45Z")
I also tried running it through space. I have an error there too
---
**Author:**  [@asif00](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fasif00)%5C
**Post date:** [May 6, 2024, 3:16pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-inference-api-error%2F85265%2F5 "2024-05-06T15:16:48Z")
> [@dilolo](#):
>
> XLM-RoBERTa
Could you please try the `XLMRobertaTokenizer` tokenizer instead of `AutoTokenizer` and let me know?
---
**Author:**  [@dilolo](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdilolo)%5C
**Post date:** [May 6, 2024, 5:50pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-inference-api-error%2F85265%2F6 "2024-05-06T17:50:59Z")
@asif00 Asif thank you very much. I really should have used the XLMRobertaTokenizer
Thanks
---
**Author:**  [@asif00](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fasif00)%5C
**Post date:** [May 6, 2024, 6:10pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-inference-api-error%2F85265%2F7 "2024-05-06T18:10:32Z")
You are welcome!!!
---
**Author:**  [@system](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsystem)%5C
**Post date:** [May 7, 2024, 6:10am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-inference-api-error%2F85265%2F8 "2024-05-07T06:10:34Z")
This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.