Token Classification
Transformers
Safetensors
lfm2
liquid
lfm2.5
bidirectional
masked-lm
encoder
pii
ner
privacy
multilingual
custom_code
Instructions to use LiquidAI/LFM2.5-Encoder-350M-PII-Detector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LiquidAI/LFM2.5-Encoder-350M-PII-Detector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="LiquidAI/LFM2.5-Encoder-350M-PII-Detector", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2.5-Encoder-350M-PII-Detector", trust_remote_code=True) model = AutoModelForTokenClassification.from_pretrained("LiquidAI/LFM2.5-Encoder-350M-PII-Detector", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
leaderboard: fair GLiNER prompting
Browse files
README.md
CHANGED
|
@@ -56,8 +56,8 @@ _clean · synthetic · tests PII-vs-NER discrimination_
|
|
| 56 |
|---|---|---|---|---|
|
| 57 |
| trained:pii-detect-v3a | 0.304 | 0.742 | 0.431 | 0.576 |
|
| 58 |
| regex baseline | 0.259 | 0.579 | 0.358 | 0.464 |
|
|
|
|
| 59 |
| openai/privacy-filter | 0.169 | 0.595 | 0.264 | 0.396 |
|
| 60 |
-
| VAGOsolutions/SauerkrautLM-GLiNER | 0.160 | 0.513 | 0.244 | 0.356 |
|
| 61 |
| iiiorg/piiranha-v1 | 0.159 | 0.422 | 0.230 | 0.317 |
|
| 62 |
| OpenMed/privacy-filter-nemotron | 0.143 | 0.545 | 0.226 | 0.348 |
|
| 63 |
| LiquidAI demo (LFM2.5-PII-Demo) | 0.132 | 0.350 | 0.192 | 0.263 |
|
|
@@ -70,7 +70,7 @@ _clean · synthetic English_
|
|
| 70 |
| trained:pii-detect-v3a | 0.815 | 0.850 | 0.832 | 0.843 |
|
| 71 |
| LiquidAI demo (LFM2.5-PII-Demo) | 0.887 | 0.735 | 0.804 | 0.761 |
|
| 72 |
| OpenMed/privacy-filter-nemotron | 0.762 | 0.773 | 0.767 | 0.770 |
|
| 73 |
-
| VAGOsolutions/SauerkrautLM-GLiNER | 0.
|
| 74 |
| iiiorg/piiranha-v1 | 0.633 | 0.490 | 0.552 | 0.513 |
|
| 75 |
| openai/privacy-filter | 0.455 | 0.462 | 0.459 | 0.461 |
|
| 76 |
| regex baseline | 0.500 | 0.254 | 0.337 | 0.281 |
|
|
@@ -81,8 +81,8 @@ _clean · human gold · English legal (ECHR)_
|
|
| 81 |
| Model | P | R | F1 | F2 |
|
| 82 |
|---|---|---|---|---|
|
| 83 |
| trained:pii-detect-v3a | 0.897 | 0.746 | 0.815 | 0.772 |
|
|
|
|
| 84 |
| OpenMed/privacy-filter-nemotron | 0.728 | 0.625 | 0.673 | 0.643 |
|
| 85 |
-
| VAGOsolutions/SauerkrautLM-GLiNER | 0.984 | 0.406 | 0.575 | 0.460 |
|
| 86 |
| openai/privacy-filter | 0.933 | 0.383 | 0.543 | 0.434 |
|
| 87 |
| LiquidAI demo (LFM2.5-PII-Demo) | 0.995 | 0.325 | 0.490 | 0.375 |
|
| 88 |
| iiiorg/piiranha-v1 | 0.721 | 0.160 | 0.262 | 0.189 |
|
|
@@ -94,7 +94,7 @@ _clean · human gold · multilingual EU legal_
|
|
| 94 |
| Model | P | R | F1 | F2 |
|
| 95 |
|---|---|---|---|---|
|
| 96 |
| trained:pii-detect-v3a | 0.499 | 0.473 | 0.486 | 0.478 |
|
| 97 |
-
| VAGOsolutions/SauerkrautLM-GLiNER | 0.
|
| 98 |
| iiiorg/piiranha-v1 | 0.465 | 0.181 | 0.261 | 0.206 |
|
| 99 |
| openai/privacy-filter | 0.372 | 0.186 | 0.248 | 0.207 |
|
| 100 |
| LiquidAI demo (LFM2.5-PII-Demo) | 0.274 | 0.140 | 0.185 | 0.155 |
|
|
@@ -111,7 +111,7 @@ _⚠ in-distribution for OpenMed-nemotron & nvidia GLiNER (read as ceilings)_
|
|
| 111 |
| OpenMed/privacy-filter-nemotron | 0.970 | 0.872 | 0.918 | 0.890 |
|
| 112 |
| LiquidAI demo (LFM2.5-PII-Demo) | 0.894 | 0.518 | 0.656 | 0.566 |
|
| 113 |
| iiiorg/piiranha-v1 | 0.841 | 0.538 | 0.656 | 0.580 |
|
| 114 |
-
| VAGOsolutions/SauerkrautLM-GLiNER | 0.
|
| 115 |
| trained:pii-detect-v3a | 0.807 | 0.516 | 0.629 | 0.556 |
|
| 116 |
| openai/privacy-filter | 0.699 | 0.484 | 0.572 | 0.516 |
|
| 117 |
| regex baseline | 0.645 | 0.227 | 0.335 | 0.260 |
|
|
@@ -123,7 +123,7 @@ _⚠ in OUR backbone's pretraining — contaminated for us; reference only_
|
|
| 123 |
|---|---|---|---|---|
|
| 124 |
| iiiorg/piiranha-v1 | 0.969 | 0.924 | 0.946 | 0.932 |
|
| 125 |
| LiquidAI demo (LFM2.5-PII-Demo) | 0.533 | 0.464 | 0.496 | 0.476 |
|
| 126 |
-
| VAGOsolutions/SauerkrautLM-GLiNER | 0.
|
| 127 |
| OpenMed/privacy-filter-nemotron | 0.341 | 0.541 | 0.418 | 0.484 |
|
| 128 |
| openai/privacy-filter | 0.316 | 0.492 | 0.385 | 0.443 |
|
| 129 |
| trained:pii-detect-v3a | 0.339 | 0.442 | 0.384 | 0.416 |
|
|
|
|
| 56 |
|---|---|---|---|---|
|
| 57 |
| trained:pii-detect-v3a | 0.304 | 0.742 | 0.431 | 0.576 |
|
| 58 |
| regex baseline | 0.259 | 0.579 | 0.358 | 0.464 |
|
| 59 |
+
| VAGOsolutions/SauerkrautLM-GLiNER | 0.171 | 0.785 | 0.280 | 0.456 |
|
| 60 |
| openai/privacy-filter | 0.169 | 0.595 | 0.264 | 0.396 |
|
|
|
|
| 61 |
| iiiorg/piiranha-v1 | 0.159 | 0.422 | 0.230 | 0.317 |
|
| 62 |
| OpenMed/privacy-filter-nemotron | 0.143 | 0.545 | 0.226 | 0.348 |
|
| 63 |
| LiquidAI demo (LFM2.5-PII-Demo) | 0.132 | 0.350 | 0.192 | 0.263 |
|
|
|
|
| 70 |
| trained:pii-detect-v3a | 0.815 | 0.850 | 0.832 | 0.843 |
|
| 71 |
| LiquidAI demo (LFM2.5-PII-Demo) | 0.887 | 0.735 | 0.804 | 0.761 |
|
| 72 |
| OpenMed/privacy-filter-nemotron | 0.762 | 0.773 | 0.767 | 0.770 |
|
| 73 |
+
| VAGOsolutions/SauerkrautLM-GLiNER | 0.605 | 0.734 | 0.663 | 0.704 |
|
| 74 |
| iiiorg/piiranha-v1 | 0.633 | 0.490 | 0.552 | 0.513 |
|
| 75 |
| openai/privacy-filter | 0.455 | 0.462 | 0.459 | 0.461 |
|
| 76 |
| regex baseline | 0.500 | 0.254 | 0.337 | 0.281 |
|
|
|
|
| 81 |
| Model | P | R | F1 | F2 |
|
| 82 |
|---|---|---|---|---|
|
| 83 |
| trained:pii-detect-v3a | 0.897 | 0.746 | 0.815 | 0.772 |
|
| 84 |
+
| VAGOsolutions/SauerkrautLM-GLiNER | 0.843 | 0.576 | 0.685 | 0.615 |
|
| 85 |
| OpenMed/privacy-filter-nemotron | 0.728 | 0.625 | 0.673 | 0.643 |
|
|
|
|
| 86 |
| openai/privacy-filter | 0.933 | 0.383 | 0.543 | 0.434 |
|
| 87 |
| LiquidAI demo (LFM2.5-PII-Demo) | 0.995 | 0.325 | 0.490 | 0.375 |
|
| 88 |
| iiiorg/piiranha-v1 | 0.721 | 0.160 | 0.262 | 0.189 |
|
|
|
|
| 94 |
| Model | P | R | F1 | F2 |
|
| 95 |
|---|---|---|---|---|
|
| 96 |
| trained:pii-detect-v3a | 0.499 | 0.473 | 0.486 | 0.478 |
|
| 97 |
+
| VAGOsolutions/SauerkrautLM-GLiNER | 0.487 | 0.258 | 0.337 | 0.285 |
|
| 98 |
| iiiorg/piiranha-v1 | 0.465 | 0.181 | 0.261 | 0.206 |
|
| 99 |
| openai/privacy-filter | 0.372 | 0.186 | 0.248 | 0.207 |
|
| 100 |
| LiquidAI demo (LFM2.5-PII-Demo) | 0.274 | 0.140 | 0.185 | 0.155 |
|
|
|
|
| 111 |
| OpenMed/privacy-filter-nemotron | 0.970 | 0.872 | 0.918 | 0.890 |
|
| 112 |
| LiquidAI demo (LFM2.5-PII-Demo) | 0.894 | 0.518 | 0.656 | 0.566 |
|
| 113 |
| iiiorg/piiranha-v1 | 0.841 | 0.538 | 0.656 | 0.580 |
|
| 114 |
+
| VAGOsolutions/SauerkrautLM-GLiNER | 0.707 | 0.583 | 0.639 | 0.604 |
|
| 115 |
| trained:pii-detect-v3a | 0.807 | 0.516 | 0.629 | 0.556 |
|
| 116 |
| openai/privacy-filter | 0.699 | 0.484 | 0.572 | 0.516 |
|
| 117 |
| regex baseline | 0.645 | 0.227 | 0.335 | 0.260 |
|
|
|
|
| 123 |
|---|---|---|---|---|
|
| 124 |
| iiiorg/piiranha-v1 | 0.969 | 0.924 | 0.946 | 0.932 |
|
| 125 |
| LiquidAI demo (LFM2.5-PII-Demo) | 0.533 | 0.464 | 0.496 | 0.476 |
|
| 126 |
+
| VAGOsolutions/SauerkrautLM-GLiNER | 0.403 | 0.610 | 0.485 | 0.553 |
|
| 127 |
| OpenMed/privacy-filter-nemotron | 0.341 | 0.541 | 0.418 | 0.484 |
|
| 128 |
| openai/privacy-filter | 0.316 | 0.492 | 0.385 | 0.443 |
|
| 129 |
| trained:pii-detect-v3a | 0.339 | 0.442 | 0.384 | 0.416 |
|