Instructions to use mrm8488/mobilebert-finetuned-ner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mrm8488/mobilebert-finetuned-ner with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="mrm8488/mobilebert-finetuned-ner")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("mrm8488/mobilebert-finetuned-ner") model = AutoModelForTokenClassification.from_pretrained("mrm8488/mobilebert-finetuned-ner") - Notebooks
- Google Colab
- Kaggle
Not working after converting to PyToch Lite
#2
by mujahidkhan - opened
@mrm8488 Can you please help me, I converted this model to PyTorch Lite and then shipped that ptl file to my Android app but when tested the .ptl file on my computer it was performing well. But my Android app is making wrong predictions the raw logit numbers are larger too.
I am very new to those, can you please give any hint on that? I also tried to convert to TensorflowLite but it was not working after the conversion. TensorFlow version works but the TensorFlowLite doesn't work.
I really need to ship this inside my Android app to work offline, Thanks in advance if you have any clue for me.
Best
Mujahid