This model is trained to perform text anonymization with proper JSON output format. It can identify and replace personally identifiable information (PII) while maintaining semantic meaning and context.

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model
model = AutoModelForCausalLM.from_pretrained("eternis/qwen1.7b-anonymizer-merged", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("eternis/qwen1.7b-anonymizer-merged", trust_remote_code=True)

# Example usage
input_text = "John Doe works at Google in New York"
# ... generate anonymized output with tool calls

Training

This model was trained using a LoRA adapter approach:

Base Qwen1.7B SFT model with tool calling capabilities
LoRA adapter specialized in anonymization tasks

License

MIT License