Instructions to use jjzha/jobberta-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jjzha/jobberta-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="jjzha/jobberta-base")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("jjzha/jobberta-base") model = AutoModelForMaskedLM.from_pretrained("jjzha/jobberta-base") - Notebooks
- Google Colab
- Kaggle
Is there anyway to use this to generate embeddings?
#1
by ddeisadze - opened
Hi, I'd like to generate embeddings for job based context. Could we leverage this model for that?
Hi David, thanks for your interest. This is a model based on RoBERTa. You can always generate embeddings from your job based context by tokenizing your text and then encoding it with the model (e.g., https://huggingface.co/learn/nlp-course/chapter2/6).
If you instead want something like sentence embeddings from the popular sentence-transformers, this model hasn't been trained for that. Thus you would need to train this model to give you strong sentence embeddings.
jjzha changed discussion status to closed