# Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("mathugo/crypto_news_bert")
model = AutoModelForMaskedLM.from_pretrained("mathugo/crypto_news_bert")CryptoBERT is a pre-trained BERT (Bidirectional Encoder Representations from Transformers) model fine-tuned on a dataset of crypto-related news articles. It is designed to analyze and understand crypto news, providing valuable insights into the rapidly evolving world of cryptocurrencies.
Features
Domain-Specific Knowledge: Trained on a diverse dataset of crypto news, CryptoBERT captures domain-specific information, enabling it to understand the unique language and context of the cryptocurrency space.
Sentiment Analysis: CryptoBERT is capable of sentiment analysis, helping you gauge the overall sentiment expressed in crypto news articles, whether it's positive, negative, or neutral.
Named Entity Recognition (NER): The model excels in identifying key entities such as cryptocurrency names, organizations, and important figures, enhancing its ability to extract relevant information.
Fine-tuned for Crypto Jargon: CryptoBERT is fine-tuned to recognize and understand the specialized jargon commonly used in the crypto industry, ensuring accurate interpretation of news articles.
Usage
- Downloads last month
- 9
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="mathugo/crypto_news_bert")