Upload folder using huggingface_hub

README.md

@@ -1,13 +1,27 @@
 ---
-title: Gliner Stream Pii Demo
-emoji: 📚
-colorFrom: pink
-colorTo: purple
+title: GLiNER Streaming PII Detector
+emoji: 🔍
+colorFrom: gray
+colorTo: indigo
 sdk: gradio
 sdk_version: 6.20.0
-python_version: '3.12'
 app_file: app.py
-pinned: false
+short_description: Zero-shot PII detection with GLiNER streaming-span model
+python_version: "3.12"
+startup_duration_timeout: 30m
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# GLiNER Streaming PII Detector
+
+This Space demonstrates [knowledgator/gliner-stream-pii-v1.0](https://huggingface.co/knowledgator/gliner-stream-pii-v1.0),
+a 0.6B-parameter zero-shot PII/NER model built on a Qwen3 backbone using the
+GLiNER streaming-span architecture.
+
+## How it works
+
+- Paste any text that may contain personally identifiable information (PII).
+- Specify the entity types you want to detect (person, email, phone number, etc.).
+- Adjust the confidence threshold to control precision vs. recall.
+- The model highlights detected entities directly in the text and lists them in a table.
+
+The model is **open-label** — you can use any entity type name, not just the defaults.

app.py

@@ -0,0 +1,220 @@
+import spaces  # MUST come before torch / any CUDA-touching import
+import torch
+import json
+import re
+import gradio as gr
+from gliner import GLiNER
+
+MODEL_ID = "knowledgator/gliner-stream-pii-v1.0"
+
+# Load the model at module scope, .to("cuda") eagerly (ZeroGPU rule 2)
+model = GLiNER.from_pretrained(
+    MODEL_ID,
+    load_tokenizer=True,
+    map_location="cuda",
+    dtype="bfloat16",
+).eval()
+
+# Default PII labels from the model card
+DEFAULT_LABELS = [
+    "person",
+    "email address",
+    "phone number",
+    "street address",
+    "credit card number",
+    "passport number",
+    "date of birth",
+    "social security number",
+    "bank account number",
+    "organization",
+]
+
+# Pastel-ish colors per entity label for highlighting
+LABEL_COLORS = [
+    "#FF6B6B",  # red-ish
+    "#4ECDC4",  # teal
+    "#95E1D3",  # green
+    "#FFE66D",  # yellow
+    "#FF8A5C",  # orange
+    "#C7B8EA",  # purple
+    "#6CB7FF",  # blue
+    "#F4A4C0",  # pink
+    "#B8E986",  # lime
+    "#E0BBE4",  # lavender
+]
+
+
+def _color_for_label(label: str) -> str:
+    idx = hash(label) % len(LABEL_COLORS)
+    return LABEL_COLORS[idx]
+
+
+def _highlight_html(text: str, entities: list) -> str:
+    """Build an HTML string that highlights detected entities in the input text."""
+    if not entities:
+        return text.replace("<", "&lt;").replace(">", "&gt;")
+
+    # Sort by start position; handle overlaps by taking longest-first
+    sorted_ents = sorted(entities, key=lambda e: (e.get("start", 0), -(e.get("end", 0) - e.get("start", 0))))
+    # De-overlap: greedy filter
+    filtered = []
+    last_end = -1
+    for ent in sorted_ents:
+        s = ent.get("start", 0)
+        e = ent.get("end", 0)
+        if s >= last_end:
+            filtered.append(ent)
+            last_end = e
+    # Re-sort by start for rendering
+    filtered.sort(key=lambda ent: ent.get("start", 0))
+
+    parts = []
+    pos = 0
+    for ent in filtered:
+        s = ent["start"]
+        e = ent["end"]
+        # Escaped plain text before this entity
+        parts.append(text[pos:s].replace("<", "&lt;").replace(">", "&gt;"))
+        ent_text = text[s:e].replace("<", "&lt;").replace(">", "&gt;")
+        label = ent["label"]
+        color = _color_for_label(label)
+        score = ent.get("score", 0)
+        tooltip = f"{label} (score: {score:.2f})"
+        parts.append(
+            f'<span style="background:{color}; border-radius:3px; '
+            f'padding:1px 3px; font-weight:600;" title="{tooltip}">{ent_text}</span>'
+        )
+        pos = e
+    parts.append(text[pos:].replace("<", "&lt;").replace(">", "&gt;"))
+    return "".join(parts)
+
+
+@spaces.GPU(duration=30)
+def detect_pii(text: str, labels_text: str, threshold: float):
+    """Detect PII entities in text using a zero-shot GLiNER model.
+
+    Args:
+        text: The input text to analyze for PII.
+        labels_text: Comma-separated list of entity types to detect.
+        threshold: Confidence threshold for entity detection (0-1).
+    """
+    if not text.strip():
+        return "<p style='color:gray;'>Enter some text to analyze…</p>", []
+
+    labels = [l.strip() for l in labels_text.split(",") if l.strip()]
+    if not labels:
+        labels = DEFAULT_LABELS
+
+    entities = model.predict_entities(text, labels, threshold=threshold)
+
+    # Build highlighted HTML
+    html = _highlight_html(text, entities)
+
+    # Build table data
+    table_rows = [
+        [ent["text"], ent["label"], f"{ent.get('score', 0):.3f}",
+         ent.get("start", 0), ent.get("end", 0)]
+        for ent in sorted(entities, key=lambda e: e.get("start", 0))
+    ]
+
+    return html, table_rows
+
+
+CSS = """
+#col-container { max-width: 1100px; margin: 0 auto; }
+.dark .gradio-container { color: var(--body-text-color); }
+"""
+
+EXAMPLES = [
+    [
+        "Jane Doe can be reached at jane.doe@example.com or at +1 (415) 555-0132. "
+        "Her credit card number is 4532-1234-5678-9010 and she lives at 123 Main St, San Francisco, CA.",
+        "person, email address, phone number, credit card number, street address",
+        0.5,
+    ],
+    [
+        "Patient John Smith (DOB: 03/15/1980, SSN: 123-45-6789) visited Mercy Hospital on Jan 5, 2025. "
+        "Contact: john.smith@email.com, account 9988776655.",
+        "person, date of birth, social security number, organization, email address, bank account number",
+        0.5,
+    ],
+    [
+        "Dear Sir, my name is Alice Chen and I would like to update my billing info. "
+        "My passport number is KL7890123 and my phone is 555-0199.",
+        "person, passport number, phone number",
+        0.5,
+    ],
+]
+
+with gr.Blocks(theme=gr.themes.Citrus(), css=CSS) as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown("# GLiNER Streaming PII Detector")
+        gr.Markdown(
+            "Zero-shot PII/NER detection with "
+            "[knowledgator/gliner-stream-pii-v1.0](https://huggingface.co/knowledgator/gliner-stream-pii-v1.0) — "
+            "a 0.6B streaming-span model built on a Qwen3 backbone. Enter any text and "
+            "the entity types you want to detect; the model highlights them in-place."
+        )
+
+        with gr.Row():
+            text_input = gr.Textbox(
+                label="Input text",
+                placeholder="Paste or type text that may contain PII…",
+                lines=8,
+                scale=4,
+            )
+            run_btn = gr.Button("Detect PII", variant="primary", scale=1)
+
+        with gr.Row():
+            labels_input = gr.Textbox(
+                label="Entity labels (comma-separated)",
+                value=", ".join(DEFAULT_LABELS),
+                scale=3,
+            )
+            threshold_slider = gr.Slider(
+                label="Confidence threshold",
+                minimum=0.0,
+                maximum=1.0,
+                value=0.5,
+                step=0.05,
+                scale=1,
+            )
+
+        gr.Markdown("### Highlighted output")
+        highlighted_output = gr.HTML(
+            value="<p style='color:gray;'>Enter some text and click Detect PII…</p>"
+        )
+
+        gr.Markdown("### Detected entities")
+        entities_table = gr.Dataframe(
+            headers=["Entity text", "Label", "Score", "Start", "End"],
+            datatype=["str", "str", "str", "number", "number"],
+            value=[],
+            interactive=False,
+            wrap=True,
+        )
+
+    run_btn.click(
+        fn=detect_pii,
+        inputs=[text_input, labels_input, threshold_slider],
+        outputs=[highlighted_output, entities_table],
+        api_name="detect_pii",
+    )
+
+    text_input.submit(
+        fn=detect_pii,
+        inputs=[text_input, labels_input, threshold_slider],
+        outputs=[highlighted_output, entities_table],
+        api_name="detect_pii_submit",
+    )
+
+    gr.Examples(
+        examples=EXAMPLES,
+        inputs=[text_input, labels_input, threshold_slider],
+        outputs=[highlighted_output, entities_table],
+        fn=detect_pii,
+        cache_examples=True,
+        cache_mode="lazy",
+    )
+
+demo.launch(mcp_server=True)

gliner_config.json

@@ -0,0 +1,147 @@
+{
+  "class_token_index": 151669,
+  "decoder_config": {
+    "_name_or_path": "Qwen/Qwen3-0.6B",
+    "architectures": [
+      "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "chunk_size_feed_forward": 0,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 40960,
+    "max_window_layers": 28,
+    "model_type": "qwen3",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 8,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": null,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 1000000,
+      "rope_type": "default"
+    },
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151671
+  },
+  "dropout": 0.3,
+  "embed_ent_token": true,
+  "encoder_config": null,
+  "ent_token": "<<ENT>>",
+  "eos_token_id": 151645,
+  "fine_tune": true,
+  "fuse_layers": false,
+  "hidden_size": 1024,
+  "id_to_classes": null,
+  "label_token": "<<LABEL>>",
+  "labels_encoder_config": {
+    "attention_probs_dropout_prob": 0.1,
+    "bos_token_id": null,
+    "eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "layer_norm_eps": 1e-07,
+    "legacy": true,
+    "max_position_embeddings": 512,
+    "max_relative_positions": 512,
+    "model_type": "deberta-v2",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 2,
+    "pad_token_id": 0,
+    "pooler_dropout": 0.0,
+    "pooler_hidden_act": "gelu",
+    "pooler_hidden_size": 1024,
+    "pos_att_type": [
+      "p2c",
+      "c2p"
+    ],
+    "position_biased_input": true,
+    "relative_attention": true,
+    "tie_word_embeddings": true,
+    "type_vocab_size": 0,
+    "vocab_size": 128100
+  },
+  "max_cache_length": null,
+  "max_len": 8192,
+  "max_neg_type_ratio": 1,
+  "max_types": 100,
+  "max_width": 12,
+  "model_name": "Qwen/Qwen3-0.6B",
+  "model_type": "gliner_streaming_span",
+  "name": "streaming span gliner",
+  "neg_spans_ratio": 1.0,
+  "num_post_fusion_layers": 1,
+  "num_rnn_layers": 0,
+  "pad_token_id": 151643,
+  "post_fusion_schema": "",
+  "precomputed_prompts_mode": null,
+  "represent_spans": false,
+  "right_context_width": 12,
+  "sep_token": "<<SEP>>",
+  "sep_token_index": 151670,
+  "span_encoder_config": null,
+  "span_loss_coef": 1.0,
+  "span_mode": "markerV2",
+  "subtoken_pooling": "first",
+  "token_loss_coef": 1.0,
+  "transformers_version": "5.6.2",
+  "use_cache": false,
+  "vocab_size": 151671,
+  "words_splitter_type": "whitespace"
+}

requirements.txt

@@ -0,0 +1,2 @@
+gliner>=0.2.28
+torch