mmBERT-32K Factcheck Classifier (Merged)

This is the merged version of the mmBERT-32K factcheck classifier model, ready for direct inference without PEFT.

Model Details

Base Model: vllm-sr/mmbert-32k-yarn
Task: Text Classification
Number of Labels: 2
Context Length: 32,768 tokens
Architecture: ModernBERT with YaRN RoPE scaling

Usage

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model = AutoModelForSequenceClassification.from_pretrained(
    "vllm-sr/mmbert32k-factcheck-classifier-merged",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("vllm-sr/mmbert32k-factcheck-classifier-merged")

# Inference
inputs = tokenizer("Your text here", return_tensors="pt", truncation=True, max_length=32768)
outputs = model(**inputs)