Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,12 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+onnx/classifier.onnx.data filter=lfs diff=lfs merge=lfs -text
+onnx/classifier_fp16.onnx.data filter=lfs diff=lfs merge=lfs -text
+onnx/count_embed.onnx.data filter=lfs diff=lfs merge=lfs -text
+onnx/count_embed_fp16.onnx.data filter=lfs diff=lfs merge=lfs -text
+onnx/encoder.onnx.data filter=lfs diff=lfs merge=lfs -text
+onnx/encoder_fp16.onnx.data filter=lfs diff=lfs merge=lfs -text
+onnx/span_rep.onnx.data filter=lfs diff=lfs merge=lfs -text
+onnx/span_rep_fp16.onnx.data filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,141 @@
+---
+library_name: gliner2-onnx
+base_model: fastino/gliner2-multi-v1
+tags:
+  - onnx
+  - gliner
+  - gliner2
+  - ner
+  - named-entity-recognition
+  - zero-shot
+  - classification
+license: mit
+---
+
+> **Experimental ONNX build** - Unofficial ONNX export of [fastino/gliner2-multi-v1](https://huggingface.co/fastino/gliner2-multi-v1).
+
+# gliner2-onnx
+
+GLiNER2 ONNX runtime for Python. Runs GLiNER2 models without PyTorch.
+
+This library is experimental. The API may change between versions.
+
+## Features
+
+- Zero-shot NER and text classification
+- Runs with ONNX Runtime (no PyTorch dependency)
+- FP32 and FP16 precision support
+- GPU acceleration via CUDA
+
+All other GLiNER2 features such as JSON export are not supported. 
+
+## Installation
+
+```bash
+pip install gliner2-onnx
+```
+
+## NER
+
+```python
+from gliner2_onnx import GLiNER2ONNXRuntime
+
+runtime = GLiNER2ONNXRuntime.from_pretrained("lmoe/gliner2-large-v1-onnx")
+
+entities = runtime.extract_entities(
+    "John works at Google in Seattle",
+    ["person", "organization", "location"]
+)
+# [
+#   Entity(text='John', label='person', start=0, end=4, score=0.98),
+#   Entity(text='Google', label='organization', start=14, end=20, score=0.97),
+#   Entity(text='Seattle', label='location', start=24, end=31, score=0.96)
+# ]
+```
+
+## Classification
+
+```python
+from gliner2_onnx import GLiNER2ONNXRuntime
+
+runtime = GLiNER2ONNXRuntime.from_pretrained("lmoe/gliner2-large-v1-onnx")
+
+# Single-label classification
+result = runtime.classify(
+    "Buy milk from the store",
+    ["shopping", "work", "entertainment"]
+)
+# {'shopping': 0.95}
+
+# Multi-label classification
+result = runtime.classify(
+    "Buy milk and finish the report",
+    ["shopping", "work", "entertainment"],
+    threshold=0.3,
+    multi_label=True
+)
+# {'shopping': 0.85, 'work': 0.72}
+```
+
+## CUDA
+
+To use CUDA for GPU acceleration:
+
+```python
+runtime = GLiNER2ONNXRuntime.from_pretrained(
+    "lmoe/gliner2-large-v1-onnx",
+    providers=["CUDAExecutionProvider", "CPUExecutionProvider"]
+)
+```
+
+## Precision
+
+Both FP32 and FP16 models are supported. Only the requested precision is downloaded.
+
+```python
+runtime = GLiNER2ONNXRuntime.from_pretrained(
+    "lmoe/gliner2-large-v1-onnx",
+    precision="fp16"
+)
+```
+
+## Models
+
+Pre-exported ONNX models:
+
+| Model | HuggingFace |
+|-------|-------------|
+| gliner2-large-v1 | [lmoe/gliner2-large-v1-onnx](https://huggingface.co/lmoe/gliner2-large-v1-onnx) |
+| gliner2-multi-v1 | [lmoe/gliner2-multi-v1-onnx](https://huggingface.co/lmoe/gliner2-multi-v1-onnx) |
+
+Note: `gliner2-base-v1` is not supported (uses a different architecture).
+
+## Exporting Models
+
+To export your own models, clone the repository and use make:
+
+```bash
+git clone https://github.com/lmoe/gliner2-onnx
+cd gliner2-onnx
+
+# FP32 only
+make onnx-export MODEL=fastino/gliner2-large-v1
+
+# FP32 + FP16
+make onnx-export MODEL=fastino/gliner2-large-v1 QUANTIZE=fp16
+```
+
+Output is saved to `model_out/<model-name>/`.
+
+## JavaScript/TypeScript
+
+For Node.js, see [@lmoe/gliner-onnx.js](https://github.com/lmoe/gliner-onnx.js).
+
+## Credits
+
+- [fastino-ai/GLiNER2](https://github.com/fastino-ai/GLiNER2) - Original GLiNER2 implementation
+- [fastino/gliner2-large-v1](https://huggingface.co/fastino/gliner2-large-v1) - Pre-trained models
+
+## License
+
+MIT

config.json

@@ -0,0 +1,4 @@
+{
+  "hidden_size": 768,
+  "vocab_size": 250101
+}

gliner2_config.json

@@ -0,0 +1,29 @@
+{
+  "max_width": 8,
+  "special_tokens": {
+    "[SEP_STRUCT]": 250102,
+    "[SEP_TEXT]": 250103,
+    "[P]": 250104,
+    "[C]": 250105,
+    "[E]": 250106,
+    "[R]": 250107,
+    "[L]": 250108,
+    "[EXAMPLE]": 250109,
+    "[OUTPUT]": 250110,
+    "[DESCRIPTION]": 250111
+  },
+  "onnx_files": {
+    "fp32": {
+      "encoder": "onnx/encoder.onnx",
+      "classifier": "onnx/classifier.onnx",
+      "span_rep": "onnx/span_rep.onnx",
+      "count_embed": "onnx/count_embed.onnx"
+    },
+    "fp16": {
+      "encoder": "onnx/encoder_fp16.onnx",
+      "classifier": "onnx/classifier_fp16.onnx",
+      "span_rep": "onnx/span_rep_fp16.onnx",
+      "count_embed": "onnx/count_embed_fp16.onnx"
+    }
+  }
+}

onnx/classifier.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0daf6bb253bf449757f507503f1204a9cd9422ec7ab15b602dcf61a70e5faaaa
+size 4731597

onnx/classifier.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a718fa8f512a3ba6f56fb7bfaace4e456f461c3b24210e79d614d5fd4c5d8b04
+size 4784128

onnx/classifier_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afb84218f428aeceee5591b02d6b5a29acf209ad6a5a1c9b8904b66430bca8c2
+size 1303

onnx/classifier_fp16.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4521c0976f0dc0625bbe05288a8b9e50af0d18828f02520ee6fe04d63d04d4ba
+size 7096320

onnx/count_embed.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b221ecf849b923733ebfde4afac2ea5a37d4a58c5252d61d037ab802c602328
+size 42506885

onnx/count_embed.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bea1328893f5cfe249537e2729e9d03ed991b6c2d53f6a73cae9ba7a9919c19
+size 42532864

onnx/count_embed_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c025e8ead7074f514304fca1f921898df8a4e8edf88d381503b03324b867de
+size 5410

onnx/count_embed_fp16.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4bc33cd6686ea5cbd2ce2e77e1dbfaad1eaeda36546fc39a7c6c73f4655324
+size 106260480

onnx/encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f225fd0164d71e3050d9ac8ba4b82bf4e6cd17b32e44f237bf36d27d4be9b1fd
+size 1111055946

onnx/encoder.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b53cd28f9d625e17f9c19c8613b9a36651b98dd8ad17b7d3e7bb0d873807c8e
+size 1110179840

onnx/encoder_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae92c5816a17ec8d88e0b19e485a081acb283e31715080cdeae3e79f4e7b3d04
+size 1265182

onnx/encoder_fp16.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d74f661dfcb9fb84407135aa79e218afc60c39adb708f2a92fc0c9b72cb49a72
+size 1665220608

onnx/span_rep.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65de283b39fcf1e73beb2ecd23ba9cf5807f2cf00ecb988944bd8d3e8d2cd144
+size 66111424

onnx/span_rep.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3944ab5ad45a9cacb3cdda9d42c80e1c7947348c9137345c54c270530a9cbad
+size 66125824

onnx/span_rep_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:544e4f98ea39687c1f8663f23435764c7628a347ce3e37a427e563cc0655cd77
+size 8387

onnx/span_rep_fp16.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8330a4d34ab4ad828b63843f01f9603caef562d64643b33a4626add34d3c14c
+size 99159552

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c7ccb287623cccb7c03150953b6d2a09dd95122933393c9151c3a60095c97e
+size 16337353

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": [
+    "[SEP_STRUCT]",
+    "[SEP_TEXT]",
+    "[P]",
+    "[C]",
+    "[E]",
+    "[R]",
+    "[L]",
+    "[EXAMPLE]",
+    "[OUTPUT]",
+    "[DESCRIPTION]"
+  ],
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {},
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}