glinerel-fast 0.1.0__tar.gz

glinerel_fast-0.1.0/.gitignore

@@ -0,0 +1,7 @@
+__pycache__/
+*.pyc
+.venv/
+dist/
+build/
+*.egg-info/
+.env

glinerel_fast-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

glinerel_fast-0.1.0/PKG-INFO

@@ -0,0 +1,161 @@
+Metadata-Version: 2.5
+Name: glinerel-fast
+Version: 0.1.0
+Summary: Fast, lightweight inference for glinerel entity, PII and relation extraction models
+Project-URL: Homepage, https://github.com/VAGOsolutions/glinerel-fast
+Project-URL: Repository, https://github.com/VAGOsolutions/glinerel-fast
+Author: Michele Montebovi
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: anonymization,gliner,inference,ner,pii,pytorch,relation-extraction
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Text Processing :: Linguistic
+Requires-Python: >=3.10
+Requires-Dist: huggingface-hub>=0.20
+Requires-Dist: numpy>=1.22
+Requires-Dist: safetensors>=0.4
+Requires-Dist: tokenizers>=0.15
+Requires-Dist: torch>=2.5
+Description-Content-Type: text/markdown
+
+# glinerel-fast
+
+Fast, lightweight inference for glinerel entity, PII and relation extraction models.
+
+* **Same predictions** as the models' reference implementation in float32 (checked on 1,288 texts, model sizes
+  72m, 128m and 314m, CPU and Apple GPU).
+* **Faster**: up to 4x lower single-text latency on CPU, up to 2x the reference's speed on the GPU, and 4-7x faster
+  loading (see [Performance](#performance)).
+* **Small**: ~1,650 lines of Python on PyTorch, NumPy, `tokenizers` and `safetensors`. No transformers, no model
+  conversion: the checkpoint's `model.safetensors` is read directly.
+* **Runs where PyTorch runs**: CPU (Linux, Windows, macOS), NVIDIA / AMD GPUs, Apple silicon GPUs. The best
+  available device is picked automatically.
+
+## Install
+
+```bash
+pip install glinerel-fast
+```
+
+For a specific PyTorch build (CPU-only, a given CUDA version, ROCm), install PyTorch first from
+[pytorch.org](https://pytorch.org/get-started/locally/). Requires Python 3.10+ and PyTorch 2.5+.
+
+The models are downloaded from the Hugging Face Hub on first use. If a repository is private, log in first
+(`hf auth login`) or set `HF_TOKEN`.
+
+## Quick start
+
+```python
+from glinerel_fast import GLiNERel
+
+model = GLiNERel.from_pretrained("path/to/glinerel-model")   # local folder or Hugging Face repository id
+
+model.extract(
+    "Hi, I'm Laura Bianchi. Reach me at +39 347 555 0192 or laura.bianchi@example.com.",
+    entities=["first name", "last name", "phone number", "email"],
+)
+# {'entities': [{'label': 'first name', 'text': 'Laura', 'start': 8, 'end': 13, 'score': 0.9986},
+#               {'label': 'last name', 'text': 'Bianchi', 'start': 14, 'end': 21, 'score': 0.9991},
+#               {'label': 'phone number', 'text': '+39 347 555 0192', 'start': 35, 'end': 51, 'score': 0.9986},
+#               {'label': 'email', 'text': 'laura.bianchi@example.com', 'start': 55, 'end': 80, 'score': 0.9972}],
+#  'relations': []}
+```
+
+### Entities and relations
+
+```python
+result = model.extract(
+    "Marie Curie was born in Warsaw in 1867. She married Pierre Curie.",
+    entities=["person", "location", "date"],
+    relations=["born in", "spouse"],
+)
+for r in result["relations"]:
+    print(r["head"]["text"], f"--[{r['label']}]-->", r["tail"]["text"], r["score"])
+# Marie Curie --[born in]--> Warsaw 0.9686
+# Marie Curie --[spouse]--> Pierre Curie 0.9479
+```
+
+`extract(texts, entities=None, relations=None, *, entity_threshold=0.5, relation_threshold=0.25, batch_size=8,
+trim_punctuation=True, merge_mentions=False)`
+
+* `texts`: one string (returns one result) or a list of strings (returns a list in the same order). Pass many texts
+  per call: they are sorted by length and batched internally.
+* `entities` / `relations`: a list of labels, or `{label: threshold}` for per-label thresholds.
+* Each result is `{"entities": [{"label", "text", "start", "end", "score"}], "relations": [{"label", "head":
+  {"text", "start", "end"}, "tail": {...}, "score"}]}`, with character offsets (`end` exclusive). Entities are sorted
+  by position, relations by score.
+* `trim_punctuation=False` keeps the model's word-level spans (`"Warsaw."`); `merge_mentions=True` keeps one relation
+  per pair of entity surfaces.
+
+### PII redaction
+
+```python
+PII = ["first name", "last name", "date of birth", "phone number", "email", "city", "passport number"]
+text = "Hi, I'm Laura Bianchi, born on 3 May 1988. Call me at +39 347 555 0192, I live in Milano."
+
+model.predict_entities(text, PII)   # GLiNER-style list of entities
+model.redact(text, PII)
+# "Hi, I'm [FIRST_NAME] [LAST_NAME], born on [DATE_OF_BIRTH]. Call me at [PHONE_NUMBER], I live in [CITY]."
+model.redact(text, PII, placeholder="<{label}>")
+```
+
+### Devices and precision
+
+```python
+GLiNERel.from_pretrained(model, device=None, precision="fp32", threads=None)
+```
+
+* `device`: `"cpu"`, `"cuda"`, `"cuda:1"`, `"mps"`; `None` picks CUDA, then MPS, then the CPU.
+* `precision`: `"fp32"` (the reference's predictions), `"bf16"` or `"fp16"` (half-precision matrix products, for
+  GPUs; 99.6-100% agreement with fp32).
+* `threads`: CPU threads. On Linux, prefer setting `OMP_NUM_THREADS` before starting Python.
+
+Tips: pass many texts per call and, on GPUs, use `batch_size=32` or more. Every label adds a few tokens to every
+text, so ask only for the labels you need. Long texts are not truncated; split very long documents by paragraph.
+
+### Command line
+
+```bash
+glinerel-fast extract --model path/to/glinerel-model --text "Contact Laura at laura@example.com" \
+    --entities person email
+glinerel-fast extract --model path/to/glinerel-model --input texts.jsonl --output out.jsonl \
+    --entities person organization --relations "works for"
+glinerel-fast bench --model path/to/glinerel-model      # time per text on this machine
+glinerel-fast info                   # versions, GPUs, default device
+```
+
+## Performance
+
+Apple M3 Pro, PyTorch 2.14, 64 PII texts with 20 PII labels, time per text. The reference is the models'
+`inference.py` on the same PyTorch and device.
+
+| Model size | Device | reference, 1 text | glinerel-fast, 1 text | reference, batch 32 | glinerel-fast, batch 32 | load |
+|---|---|---:|---:|---:|---:|---:|
+| 72m | CPU | 102.5 ms | 26.7 ms (**3.8x**) | 21.5 ms | 17.3 ms (1.2x) | 5.3 s → 0.8 s |
+| 72m | GPU (MPS) | 26.2 ms | 15.2 ms (**1.7x**) | 13.3 ms | 6.6 ms (**2.0x**) | 7.0 s → 0.9 s |
+| 128m | CPU | 155.4 ms | 37.9 ms (**4.1x**) | 30.9 ms | 24.3 ms (1.3x) | 5.4 s → 0.7 s |
+| 128m | GPU (MPS) | 24.4 ms | 17.1 ms (1.4x) | 14.2 ms | 9.2 ms (**1.5x**) | 5.5 s → 1.1 s |
+| 314m | CPU | 231.7 ms | 73.8 ms (**3.1x**) | 48.4 ms | 47.4 ms (1.0x) | 6.8 s → 1.1 s |
+| 314m | GPU (MPS) | 32.6 ms | 23.2 ms (1.4x) | 20.3 ms | 15.1 ms (1.3x) | 7.2 s → 2.0 s |
+
+On a Linux CPU (OpenBLAS) the two implementations are bound by the same matrix products and run at about the same
+speed (0.9-1.4x), with the faster loading. NVIDIA GPUs and Windows have not been benchmarked yet.
+
+Accuracy against the reference (agreement F1, the reference's predictions as gold; 1,000 PII texts in 5 languages
+and the 288 CoNLL04 test sentences):
+
+| Precision | PII entities | CoNLL04 entities | CoNLL04 relations |
+|---|---:|---:|---:|
+| fp32 (CPU, MPS), all three sizes | 1.0000 | 1.0000 | 1.0000 |
+| fp16 (MPS) | 0.9991-0.9998 | 0.9995-1.0000 | 0.9963-1.0000 |
+| *the reference's own bf16 mode, for comparison* | *0.9915-0.9926* | *0.9978-0.9990* | *0.9902-0.9967* |
+
+## License
+
+Apache-2.0 for this library. The model weights are subject to their own license on the Hugging Face Hub.

glinerel_fast-0.1.0/README.md

@@ -0,0 +1,135 @@
+# glinerel-fast
+
+Fast, lightweight inference for glinerel entity, PII and relation extraction models.
+
+* **Same predictions** as the models' reference implementation in float32 (checked on 1,288 texts, model sizes
+  72m, 128m and 314m, CPU and Apple GPU).
+* **Faster**: up to 4x lower single-text latency on CPU, up to 2x the reference's speed on the GPU, and 4-7x faster
+  loading (see [Performance](#performance)).
+* **Small**: ~1,650 lines of Python on PyTorch, NumPy, `tokenizers` and `safetensors`. No transformers, no model
+  conversion: the checkpoint's `model.safetensors` is read directly.
+* **Runs where PyTorch runs**: CPU (Linux, Windows, macOS), NVIDIA / AMD GPUs, Apple silicon GPUs. The best
+  available device is picked automatically.
+
+## Install
+
+```bash
+pip install glinerel-fast
+```
+
+For a specific PyTorch build (CPU-only, a given CUDA version, ROCm), install PyTorch first from
+[pytorch.org](https://pytorch.org/get-started/locally/). Requires Python 3.10+ and PyTorch 2.5+.
+
+The models are downloaded from the Hugging Face Hub on first use. If a repository is private, log in first
+(`hf auth login`) or set `HF_TOKEN`.
+
+## Quick start
+
+```python
+from glinerel_fast import GLiNERel
+
+model = GLiNERel.from_pretrained("path/to/glinerel-model")   # local folder or Hugging Face repository id
+
+model.extract(
+    "Hi, I'm Laura Bianchi. Reach me at +39 347 555 0192 or laura.bianchi@example.com.",
+    entities=["first name", "last name", "phone number", "email"],
+)
+# {'entities': [{'label': 'first name', 'text': 'Laura', 'start': 8, 'end': 13, 'score': 0.9986},
+#               {'label': 'last name', 'text': 'Bianchi', 'start': 14, 'end': 21, 'score': 0.9991},
+#               {'label': 'phone number', 'text': '+39 347 555 0192', 'start': 35, 'end': 51, 'score': 0.9986},
+#               {'label': 'email', 'text': 'laura.bianchi@example.com', 'start': 55, 'end': 80, 'score': 0.9972}],
+#  'relations': []}
+```
+
+### Entities and relations
+
+```python
+result = model.extract(
+    "Marie Curie was born in Warsaw in 1867. She married Pierre Curie.",
+    entities=["person", "location", "date"],
+    relations=["born in", "spouse"],
+)
+for r in result["relations"]:
+    print(r["head"]["text"], f"--[{r['label']}]-->", r["tail"]["text"], r["score"])
+# Marie Curie --[born in]--> Warsaw 0.9686
+# Marie Curie --[spouse]--> Pierre Curie 0.9479
+```
+
+`extract(texts, entities=None, relations=None, *, entity_threshold=0.5, relation_threshold=0.25, batch_size=8,
+trim_punctuation=True, merge_mentions=False)`
+
+* `texts`: one string (returns one result) or a list of strings (returns a list in the same order). Pass many texts
+  per call: they are sorted by length and batched internally.
+* `entities` / `relations`: a list of labels, or `{label: threshold}` for per-label thresholds.
+* Each result is `{"entities": [{"label", "text", "start", "end", "score"}], "relations": [{"label", "head":
+  {"text", "start", "end"}, "tail": {...}, "score"}]}`, with character offsets (`end` exclusive). Entities are sorted
+  by position, relations by score.
+* `trim_punctuation=False` keeps the model's word-level spans (`"Warsaw."`); `merge_mentions=True` keeps one relation
+  per pair of entity surfaces.
+
+### PII redaction
+
+```python
+PII = ["first name", "last name", "date of birth", "phone number", "email", "city", "passport number"]
+text = "Hi, I'm Laura Bianchi, born on 3 May 1988. Call me at +39 347 555 0192, I live in Milano."
+
+model.predict_entities(text, PII)   # GLiNER-style list of entities
+model.redact(text, PII)
+# "Hi, I'm [FIRST_NAME] [LAST_NAME], born on [DATE_OF_BIRTH]. Call me at [PHONE_NUMBER], I live in [CITY]."
+model.redact(text, PII, placeholder="<{label}>")
+```
+
+### Devices and precision
+
+```python
+GLiNERel.from_pretrained(model, device=None, precision="fp32", threads=None)
+```
+
+* `device`: `"cpu"`, `"cuda"`, `"cuda:1"`, `"mps"`; `None` picks CUDA, then MPS, then the CPU.
+* `precision`: `"fp32"` (the reference's predictions), `"bf16"` or `"fp16"` (half-precision matrix products, for
+  GPUs; 99.6-100% agreement with fp32).
+* `threads`: CPU threads. On Linux, prefer setting `OMP_NUM_THREADS` before starting Python.
+
+Tips: pass many texts per call and, on GPUs, use `batch_size=32` or more. Every label adds a few tokens to every
+text, so ask only for the labels you need. Long texts are not truncated; split very long documents by paragraph.
+
+### Command line
+
+```bash
+glinerel-fast extract --model path/to/glinerel-model --text "Contact Laura at laura@example.com" \
+    --entities person email
+glinerel-fast extract --model path/to/glinerel-model --input texts.jsonl --output out.jsonl \
+    --entities person organization --relations "works for"
+glinerel-fast bench --model path/to/glinerel-model      # time per text on this machine
+glinerel-fast info                   # versions, GPUs, default device
+```
+
+## Performance
+
+Apple M3 Pro, PyTorch 2.14, 64 PII texts with 20 PII labels, time per text. The reference is the models'
+`inference.py` on the same PyTorch and device.
+
+| Model size | Device | reference, 1 text | glinerel-fast, 1 text | reference, batch 32 | glinerel-fast, batch 32 | load |
+|---|---|---:|---:|---:|---:|---:|
+| 72m | CPU | 102.5 ms | 26.7 ms (**3.8x**) | 21.5 ms | 17.3 ms (1.2x) | 5.3 s → 0.8 s |
+| 72m | GPU (MPS) | 26.2 ms | 15.2 ms (**1.7x**) | 13.3 ms | 6.6 ms (**2.0x**) | 7.0 s → 0.9 s |
+| 128m | CPU | 155.4 ms | 37.9 ms (**4.1x**) | 30.9 ms | 24.3 ms (1.3x) | 5.4 s → 0.7 s |
+| 128m | GPU (MPS) | 24.4 ms | 17.1 ms (1.4x) | 14.2 ms | 9.2 ms (**1.5x**) | 5.5 s → 1.1 s |
+| 314m | CPU | 231.7 ms | 73.8 ms (**3.1x**) | 48.4 ms | 47.4 ms (1.0x) | 6.8 s → 1.1 s |
+| 314m | GPU (MPS) | 32.6 ms | 23.2 ms (1.4x) | 20.3 ms | 15.1 ms (1.3x) | 7.2 s → 2.0 s |
+
+On a Linux CPU (OpenBLAS) the two implementations are bound by the same matrix products and run at about the same
+speed (0.9-1.4x), with the faster loading. NVIDIA GPUs and Windows have not been benchmarked yet.
+
+Accuracy against the reference (agreement F1, the reference's predictions as gold; 1,000 PII texts in 5 languages
+and the 288 CoNLL04 test sentences):
+
+| Precision | PII entities | CoNLL04 entities | CoNLL04 relations |
+|---|---:|---:|---:|
+| fp32 (CPU, MPS), all three sizes | 1.0000 | 1.0000 | 1.0000 |
+| fp16 (MPS) | 0.9991-0.9998 | 0.9995-1.0000 | 0.9963-1.0000 |
+| *the reference's own bf16 mode, for comparison* | *0.9915-0.9926* | *0.9978-0.9990* | *0.9902-0.9967* |
+
+## License
+
+Apache-2.0 for this library. The model weights are subject to their own license on the Hugging Face Hub.

glinerel_fast-0.1.0/pyproject.toml

@@ -0,0 +1,44 @@
+[build-system]
+requires = ["hatchling>=1.24"]
+build-backend = "hatchling.build"
+
+[project]
+name = "glinerel-fast"
+version = "0.1.0"
+description = "Fast, lightweight inference for glinerel entity, PII and relation extraction models"
+readme = "README.md"
+requires-python = ">=3.10"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+authors = [{ name = "Michele Montebovi" }]
+keywords = ["pii", "ner", "relation-extraction", "gliner", "pytorch", "inference", "anonymization"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Text Processing :: Linguistic",
+]
+dependencies = [
+    "torch>=2.5",
+    "numpy>=1.22",
+    "tokenizers>=0.15",
+    "safetensors>=0.4",
+    "huggingface_hub>=0.20",
+]
+
+[project.urls]
+Homepage = "https://github.com/VAGOsolutions/glinerel-fast"
+Repository = "https://github.com/VAGOsolutions/glinerel-fast"
+
+[project.scripts]
+glinerel-fast = "glinerel_fast.cli:main"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/glinerel_fast"]
+
+[tool.hatch.build.targets.sdist]
+include = ["src/glinerel_fast", "README.md", "LICENSE", "pyproject.toml"]

glinerel_fast-0.1.0/src/glinerel_fast/__init__.py

@@ -0,0 +1,6 @@
+"""Fast, lightweight inference for glinerel entity, PII and relation extraction models."""
+
+from glinerel_fast.model import GLiNERel
+
+__version__ = "0.1.0"
+__all__ = ["GLiNERel", "__version__"]