Text Classification
Transformers
PyTorch
Safetensors
English
roberta
cryptocurrency
crypto
BERT
sentiment classification
NLP
bitcoin
ethereum
shib
social media
sentiment analysis
cryptocurrency sentiment analysis
text-embeddings-inference
Instructions to use ElKulako/cryptobert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ElKulako/cryptobert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ElKulako/cryptobert")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("ElKulako/cryptobert") model = AutoModelForSequenceClassification.from_pretrained("ElKulako/cryptobert") - Inference
- Notebooks
- Google Colab
- Kaggle
How can we extend this model to a binary classification ie Crypto related or not?
#1
by Hardik1347 - opened
Hey, really loved your project. I have recently started exploring the area of DS and will love if you can guide me for one of my own problem statements. I have just been working on a project on how can I reduce noise in the ecosystem by just filtering non-crypto related messages. Eg Telegram chats have a lot of messages, how can I just filter out messages/conversation which I don't care about. I guess we can extend your model to that as well. I know this might be a noob question, but thats what I am right now. Will love if you can guide me!
Hardik1347 changed discussion title from How can we extend this model to a binary classification ie Crypto or not? to How can we extend this model to a binary classification ie Crypto related or not?
Now that I think about it, a normal classifier would do the job! But the only problem I am having is how can I prepare labeled data to train that model?