Finetuned FinBERT Crypto

This model is a fine-tuned version of yiyanghkust/finbert-tone, optimized for sentiment analysis on crypto-related financial texts.
It was trained using custom annotated data focused on cryptocurrency news, tweets, and reports.

Model Details

• Base model: FinBERT (yiyanghkust/finbert-tone)
• Fine-tuned on: Cryptocurrency-related financial sentiment dataset
• Classes: Positive, Neutral, Negative
• Checkpoint used: checkpoint-6000
• Framework: PyTorch / Transformers

Intended Use

This model is intended for sentiment classification of financial texts in the cryptocurrency domain. It may be useful for traders, analysts, or NLP researchers working with crypto-related content.

How to Use

from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("burakutf/finetuned-finbert-crypto")
model = AutoModelForSequenceClassification.from_pretrained("burakutf/finetuned-finbert-crypto")

text = "Golden Crosses Signal Breakout Potential for Bitcoin and Altcoins"
inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=128)
outputs = model(**inputs)
pred = outputs.logits.argmax(dim=1).item()

label_map = {0: "negative", 1: "neutral", 2: "positive"}
print("Tahmin:", label_map[pred])