Text Generation
Transformers
Safetensors
Turkish
English
gemma3_text
pii
pii-detection
turkish-nlp
personal-data
data-redaction
anonymization
masking
kvkk
gdpr
turkish
privacy
on-device
data-masking
redaction
turkish-pii
text-anonymization
ner
named-entity-recognition
tckn
iban
conversational
Eval Results (legacy)
text-generation-inference
Instructions to use halilneed/turkish-pii-detection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use halilneed/turkish-pii-detection with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="halilneed/turkish-pii-detection") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("halilneed/turkish-pii-detection") model = AutoModelForCausalLM.from_pretrained("halilneed/turkish-pii-detection", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use halilneed/turkish-pii-detection with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "halilneed/turkish-pii-detection" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "halilneed/turkish-pii-detection", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/halilneed/turkish-pii-detection
- SGLang
How to use halilneed/turkish-pii-detection with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "halilneed/turkish-pii-detection" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "halilneed/turkish-pii-detection", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "halilneed/turkish-pii-detection" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "halilneed/turkish-pii-detection", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use halilneed/turkish-pii-detection with Docker Model Runner:
docker model run hf.co/halilneed/turkish-pii-detection
Commit History
Yesterday
-
Card: answer block, widget examples, demo badge, tags, related models; remove Gumroad links
Verified signature3de74b6 -
Model card: link to model page on halilneed.agency
Verified signatureaee5f20 -
Model card: top CTA, TR kit link, accurate intro
Verified signature9360694 -
Improve model card: bilingual intro, FAQ, resources
Verified signature6a81667
11 days ago
-
Link the card to halilneed.agency and the personal data guide
Verified signature350b2f8
21 days ago
-
Link the interactive client-side browser demo and document quantization limits
Verified signature25ee1e3 -
Add English technical guide and tested policy examples while preserving Turkish documentation
Verified signatureabd0512 -
Clarify Turkish PII masking usage, metadata and FAQ
Verified signature86842e3 -
Update README.md
Verified signature2864471
24 days ago
-
Link the BSEBY bank data classifier
Verified signature19c6c7d
26 days ago
-
v02: 0.944 exact match (0.880 in v01), teacher-aligned fine-tune + WiSE-FT
Verified signatureContinued training on 32.9k teacher-aligned synthetic examples, then weight interpolation with v01 (alpha 0.5). v01 remains available at revision 'v01'.0a1bb5b
27 days ago
-
Add Medium article link to model card
Verified signaturea628dcf
28 days ago
-
Remove model comparison table and author credit line
Verified signature6010dc9 -
Remove citation block from model card
Verified signature5fec581 -
Shorten model card, Turkish only, drop melikegks row
Verified signature8482c54 -
Update model card: credit starting checkpoint, fix comparison table, link companion repo
Verified signature59032ef
29 days ago
-
Update README.md
Verified signature37f0c06
-
Update README.md
Halil AtasoyVerified signaturedb008b3
-
Upload folder using huggingface_hub
Halil AtasoyVerified signature4c25b2d -
Upload folder using huggingface_hub
Halil AtasoyVerified signature8dc8448 -
initial commit
Halil AtasoyVerified signature7d40154