No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from perplexity-ai/pplx-pii-masking-GGUF
All models by perplexity-ai →GGUF packaging of
perplexity-ai/pplx-pii-masking,
a PII masking model for conversational data. The model uses a ~600M-parameter
bidirectional Qwen3 encoder with a
perplexity-ai/pplx-embed-v1-0.6b
backbone and two heads:
private_person, account_number, private_url, private_date,
private_address, private_email, private_phone, other_pii, secret),
decoded with a constrained Viterbi decoder.The backbone is provided as an f16 GGUF for llama.cpp. Both heads remain in
fp32 in heads.safetensors. The included Python client applies the heads to
per-token hidden states from llama-server, decodes PII spans, and masks text.
Install a compatible llama-server build and the Python client dependencies,
then download the repository:
Keep the server running. In a second terminal, enter the downloaded model directory and run:
The client prints sensitivity, PII spans, and masked text. It includes the
constrained BIOES Viterbi decoder and reads the label list and biases from
pii_head_config.json.
The GGUF stores qwen3.attention.causal = false for bidirectional attention.
Use --pooling none to obtain one 1024-dimensional hidden state per token.
The classification and sensitivity heads are applied separately by the client.
Use llama-server's native /embeddings endpoint for these unnormalized
per-token hidden states:
The client computes token_logits = h @ W_cls.T + b_cls, then decodes the
37 BIOES labels with constrained Viterbi. Sequence sensitivity is
sigmoid(mean_pool(h) @ W_sen.T + b_sen).
Tokenization and character offsets use the supplied tokenizer files.
-b and -ub at 4096 for the supported input window./v1/embeddings does not support --pooling none; use /embeddings.MIT, matching the base model. See LICENSE [blocked].
pip install huggingface_hub torch safetensors transformershf download perplexity-ai/pplx-pii-masking-GGUF --local-dir pplx-pii-masking-GGUFcd pplx-pii-masking-GGUFllama-server -m pplx-pii-masking-backbone-f16.gguf \ --host 127.0.0.1 --port 8080 \ --embeddings --pooling none -c 4096 -b 4096 -ub 4096python example_client.py \ "Hi, I'm Daniel Whitfield, you can reach me at daniels@meridiancap.com or 415-555-0123."curl -s http://127.0.0.1:8080/embeddings \ -H 'Content-Type: application/json' \ -d '{"content":"My email is daniels@meridiancap.com"}'