pedrovo9/bge-reranker-v2-m3-multirag-finetuned

BGE Reranker v2-m3 - Multi-domain RAG Fine-tuned

Fine-tuned version of BAAI/bge-reranker-v2-m3 for multi-domain reranking.

Training Details

• Base model: BAAI/bge-reranker-v2-m3
• Training strategy: Pairwise learning (1:2 ratio)
• Hard negatives: BM25
• Epochs: 3

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

tokenizer = AutoTokenizer.from_pretrained("pedrovo9/bge-reranker-v2-m3-multirag-finetuned")
model = AutoModelForSequenceClassification.from_pretrained("pedrovo9/bge-reranker-v2-m3-multirag-finetuned")

query = "What is cloud computing?"
document = "Cloud computing is..."

inputs = tokenizer(query, document, return_tensors='pt', truncation=True, max_length=512)
with torch.no_grad():
    score = torch.sigmoid(model(**inputs).logits[0, 0]).item()