Instructions to use halilneed/turkish-pii-detection-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use halilneed/turkish-pii-detection-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf halilneed/turkish-pii-detection-GGUF:BF16 # Run inference directly in the terminal: llama cli -hf halilneed/turkish-pii-detection-GGUF:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf halilneed/turkish-pii-detection-GGUF:BF16 # Run inference directly in the terminal: llama cli -hf halilneed/turkish-pii-detection-GGUF:BF16
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf halilneed/turkish-pii-detection-GGUF:BF16 # Run inference directly in the terminal: ./build/bin/llama cli -hf halilneed/turkish-pii-detection-GGUF:BF16
Use Docker
docker model run hf.co/halilneed/turkish-pii-detection-GGUF:BF16
- Llama new
- LM Studio
- Jan
- vLLM
How to use halilneed/turkish-pii-detection-GGUF 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-GGUF" # 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-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/halilneed/turkish-pii-detection-GGUF:BF16
- Ollama
How to use halilneed/turkish-pii-detection-GGUF with Ollama:
ollama run hf.co/halilneed/turkish-pii-detection-GGUF:BF16
- Unsloth Desktop
- Docker Model Runner
How to use halilneed/turkish-pii-detection-GGUF with Docker Model Runner:
docker model run hf.co/halilneed/turkish-pii-detection-GGUF:BF16
- Lemonade
How to use halilneed/turkish-pii-detection-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull halilneed/turkish-pii-detection-GGUF:BF16
Run and chat with the model
lemonade run user.turkish-pii-detection-GGUF-BF16
List all available models
lemonade list
- Atomic Chat
turkish-pii-detection-GGUF
What is this model? turkish-pii-detection-GGUF is the GGUF (BF16, Q8_0) build of halilneed/turkish-pii-detection for local PII masking of Turkish text with Ollama or llama.cpp on CPU, without Python or transformers.
EN: Turkish PII detection / KVKK data masking, offline β GGUF (BF16, Q8_0) build for Ollama and llama.cpp. TR: TΓΌrkΓ§e kiΕisel veri tespiti / KVKK veri maskeleme, Γ§evrimdΔ±ΕΔ± β Ollama ve llama.cpp iΓ§in GGUF (BF16, Q8_0) sΓΌrΓΌmΓΌ. Model page & setup help / Model sayfasΔ± ve kurulum desteΔi: halilneed.agency/models/turkish-pii-detection
halilneed/turkish-pii-detection v02'nin GGUF sΓΌrΓΌmΓΌ: Ollama ve llama.cpp ile yerelde, Python ve transformers olmadan Γ§alΔ±ΕΔ±r. TΓΌrkΓ§e metindeki kiΕisel verileri (ad, TCKN, IBAN, telefon, e-posta, adres ve 53 etiketin geri kalanΔ±) metin bir LLM'e ya da log deposuna gitmeden ΓΆnce etiketle deΔiΕtirir; maskeleme politikasΔ±nΔ± talimat olarak okur.
Files / Dosyalar: turkish-pii-detection-Q8_0.gguf 299.7 MB (299,748,544 bytes) Β· turkish-pii-detection-BF16.gguf 551.0 MB (551,038,144 bytes). Runs on CPU, no GPU needed (llama.cpp / Ollama) / GPU gerekmez, CPU'da Γ§alΔ±ΕΔ±r. Try the browser demo / TarayΔ±cΔ± demosunu deneyin (demo runs the base model's ONNX conversion, not these GGUF files / demo bu GGUF dosyalarΔ±nΔ± deΔil ana modelin ONNX dΓΆnΓΌΕΓΌmΓΌnΓΌ Γ§alΔ±ΕtΔ±rΔ±r).
| Dosya | Boyut | Benchmark (1.000 satΔ±r, tam eΕleΕme) | Ana modelle aynΔ± Γ§Δ±ktΔ± |
|---|---|---|---|
| ana model, transformers BF16 | 536 MB | 0.944 | β |
turkish-pii-detection-BF16.gguf |
551 MB | 0.943 | %99,6 |
turkish-pii-detection-Q8_0.gguf |
300 MB | 0.944 | %98,9 |
ΓlΓ§ΓΌm: cagrigungor/turkish-pii-masking-benchmark, satΔ±r dΓΌzeyi tam eΕleΕme (strip sonrasΔ± karakter karakter aynΔ±), ana model kartΔ±ndaki betikle aynΔ± metrik. GGUF'lar Ollama 0.40.7 ΓΌzerinden, sΔ±caklΔ±k 0 ile koΕuldu. Model tahminini yaptΔ±ΔΔ± 1.000 satΔ±rΔ±n 996'sΔ±nda (BF16) ve 989'unda (Q8_0) ana modelle birebir aynΔ± Γ§Δ±ktΔ±yΔ± verdi.
Q8_0'Δ±n zayΔ±f dilimleri ana modelle aynΔ±: ek almΔ±Ε PII 0.803, BΓYΓK HARF 0.847. Tek fark, 20 satΔ±rlΔ±k Γ§ok kiΕili metin diliminde: 0.650, ana modelde 0.750 (iki satΔ±r). Γok kiΕili metinleri maskeliyorsan BF16'yΔ± kullan.
Q4_K_M yok: modelin 268M parametresinin 168M'i embedding tablosunda ve Q8_0 zaten 300 MB. 4 bitlik sΓΌrΓΌmΓΌ kΓΌΓ§ΓΌk bir modelde kaybΔ±nΔ± ΓΆlΓ§meden yayΔ±nlamΔ±yorum.
Ollama
ollama pull hf.co/halilneed/turkish-pii-detection-GGUF:Q8_0
Deterministik Γ§Δ±ktΔ± ve doΔru durma iΓ§in bu repodaki Modelfile ile kendi adΔ±nΔ± ver:
# Modelfile ve .gguf aynΔ± klasΓΆrde
ollama create turkish-pii -f Modelfile
ollama run turkish-pii "Metindeki tΓΌm kiΕisel verileri uygun etiketlerle maskele.
Metin: mΓΌΕteri AyΕe YΔ±lmaz tc 12345678950 tel 0532 111 22 33"
# -> mΓΌΕteri [AD] tc [TCKN] tel [TEL]
Δ°stek her zaman <talimat>, boΕ satΔ±r, Metin: <metin> biΓ§imindedir. Talimat politikayΔ± belirler: "Sadece telefon numaralarΔ±nΔ± maskele", "TCKN dΔ±ΕΔ±ndaki her Εeyi maskele" gibi. Politikalar ve 53 etiketlik Εema ana model kartΔ±nda.
Python'dan, Ollama'nΔ±n yerel API'siyle:
import json, urllib.request
def maskele(metin, talimat="Metindeki tΓΌm kiΕisel verileri uygun etiketlerle maskele."):
body = {"model": "turkish-pii", "prompt": f"{talimat}\n\nMetin: {metin}", "stream": False,
"options": {"temperature": 0}}
req = urllib.request.Request("http://127.0.0.1:11434/api/generate", json.dumps(body).encode(),
{"Content-Type": "application/json"})
return json.loads(urllib.request.urlopen(req).read())["response"].strip()
llama.cpp
llama-cli -hf halilneed/turkish-pii-detection-GGUF:Q8_0 --temp 0 -n 512
DΓΆnΓΌΕtΓΌrme
- llama.cpp
convert_hf_to_gguf.py(commit1ab09d6),--outtype bf16ve--outtype q8_0, ana modelin v02 aΔΔ±rlΔ±ΔΔ±ndan (sha256 Hub'dakimodel.safetensorsile aynΔ±). - Ana modelin tokenizer'Δ±nda embedding tablosunda karΕΔ±lΔ±ΔΔ± olmayan bir token var: Gemma 3'ΓΌn gΓΆrsel tokenΔ±
<image_soft_token>(id 262144). DΓΆnΓΌΕtΓΌrΓΌcΓΌ bunu kabul etmediΔi iΓ§in dΓΆnΓΌΕtΓΌrme kopyasΔ±ndan Γ§Δ±karΔ±ldΔ±. Benchmark'Δ±n 1.000 promptu ve 1.000 beklenen Γ§Δ±ktΔ±sΔ±nda tokenizasyon birebir aynΔ± kaldΔ±. - Ollama 0.40.7 safetensors iΓ§e aktarmada Gemma 3'ΓΌ desteklemiyor; bu yΓΌzden GGUF.
SΔ±nΔ±rlar
Ana modelin sΔ±nΔ±rlarΔ± geΓ§erli: sentetik veriyle deΔerlendirildi, ΓΌretimden ΓΆnce kendi metninde ΓΆlΓ§; baΔlamsΔ±z kΔ±sa parΓ§alarda temkinli; Εema dΔ±ΕΔ± etiket ΓΌretebilir, Γ§Δ±ktΔ±yΔ± etiket listesine karΕΔ± doΔrula. KVKK/GDPR uyumu kullananΔ±n sorumluluΔundadΔ±r. Lisans: Gemma Terms of Use.
English
GGUF build of halilneed/turkish-pii-detection v02, a 270M model that masks Turkish personal data (names, national ID numbers, IBANs, phone numbers, emails, addresses; 53 labels) following a Turkish instruction. Runs locally with Ollama or llama.cpp. On the 1,000-row cagrigungor/turkish-pii-masking-benchmark, Q8_0 (300 MB) scores 0.944 row-level exact match, the same as the original model, and BF16 scores 0.943. The one difference is the 20-row multi-person slice, where Q8_0 scores 0.650 against 0.750. The prompt is <instruction>, a blank line, then Metin: <text>; use the Modelfile here for temperature 0 and the right stop token.
Model page with every result: halilneed.agency/models/turkish-pii-detection
Related models / Δ°lgili modeller
- halilneed/turkish-pii-detection β instruction-conditioned PII masking / talimatla kiΕisel veri maskeleme (270M)
- halilneed/turkish-pii-detection-GGUF β GGUF (BF16, Q8_0) for Ollama & llama.cpp, CPU / Γ§evrimdΔ±ΕΔ± GGUF sΓΌrΓΌmΓΌ (this model / bu model)
- halilneed/turkish-kvkk-classifier β KVKK / VERBΔ°S personal-data category classifier / kiΕisel veri kategori sΔ±nΔ±flandΔ±rΔ±cΔ±
- halilneed/turkish-bseby-classifier β BSEBY banking data & secrecy classifier / bankacΔ±lΔ±k veri ve sΔ±r sΔ±nΔ±flandΔ±rΔ±cΔ±
- halilneed/turkish-prompt-injection-classifier β Turkish prompt injection detection / TΓΌrkΓ§e prompt injection tespiti
All five in one collection / Hepsi tek koleksiyonda: Turkish Privacy & Safety Models
FAQ / SΔ±k sorulan sorular
Which file should I use? / Hangi dosyayΔ± kullanmalΔ±yΔ±m? Q8_0 (300 MB) scores 0.944 row-level exact match on the 1,000-row benchmark, same as the original model; BF16 (551 MB) scores 0.943. On the 20-row multi-person slice Q8_0 scores 0.650 vs 0.750, so use BF16 for multi-person texts. / Γok kiΕili metinler iΓ§in BF16 ΓΆnerilir.
Is there a Q4_K_M build? / Q4_K_M sΓΌrΓΌmΓΌ var mΔ±? No. 168M of the 268M parameters are in the embedding table and Q8_0 is already 300 MB; a 4-bit build is not published without measuring its loss. / HayΔ±r, kaybΔ± ΓΆlΓ§ΓΌlmeden yayΔ±nlanmΔ±yor.
What is the prompt format? / Δ°stek biΓ§imi nedir?
<instruction>, a blank line, then Metin: <text>. Use the Modelfile in this repo for temperature 0 and the right stop token. / Talimat maskeleme politikasΔ±nΔ± belirler.
Does it guarantee KVKK/GDPR compliance? / KVKK/GDPR uyumu saΔlar mΔ±? No. It was evaluated on synthetic data; measure on your own text, validate labels against the schema. Compliance is the user's responsibility. / Uyum kullananΔ±n sorumluluΔundadΔ±r.
Resources / Kaynaklar
- halilneed agency: halilneed.agency/models/turkish-pii-detection
- Downloads last month
- 1,177
8-bit
16-bit
Model tree for halilneed/turkish-pii-detection-GGUF
Base model
google/gemma-3-270m