GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
LorenzoMascia
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
LorenzoMascia
Model Tree
TinyLlama/TinyLlama-1.1B-Chat-v1.0
Input Modalities
Output Modalities
Supported Functionality
Input:
markdown
Mario Rossi lives at Via Roma 1, Milano. Email: m.rossi@email.com
Output:
json
{"anonymized_text": "[NAME_1] lives at [ADDRESS_1]. Email: [EMAIL_1]","replaced_tokens": [{"replaced_value": "[NAME_1]", "original_value": "Mario Rossi"},{"replaced_value": "[ADDRESS_1]", "original_value": "Via Roma 1, Milano"},{"replaced_value": "[EMAIL_1]", "original_value": "m.rossi@email.com"}]}
These are LoRA adapters — the base model weights are not included.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelBASE = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"tokenizer = AutoTokenizer.from_pretrained(BASE)model = AutoModelForCausalLM.from_pretrained(BASE, torch_dtype=torch.float16, device_map="auto")model = PeftModel.from_pretrained(model, "LorenzoMascia/tinyllama-lora-anonymizer")
The adapters were trained on the Alpaca template. Using a different format will degrade output quality significantly.
markdown
### Instruction:Analyze the following text and anonymize all personally identifiable information (PII). Return a JSON object with the anonymized text and all replaced tokens.### Input:{your text here}### Response:
Generate with a low temperature (~0.1) — the output is a data structure, not prose.
q_proj, v_projTraining an anonymizer would normally require a corpus of real PII — precisely the data the model is meant to protect. Synthetic generation resolves that: the teacher produces realistic input/output pairs, and the student learns from those alone.
Apache 2.0