Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ 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/count_embed.onnx.data filter=lfs diff=lfs merge=lfs -text
+onnx/count_embed_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: hivetrace/gliner-guard-uniencoder
+tags:
+  - onnx
+  - gliner
+  - gliner2
+  - ner
+  - named-entity-recognition
+  - zero-shot
+  - classification
+license: mit
+---
+
+> **Experimental ONNX build** - Unofficial ONNX export of [hivetrace/gliner-guard-uniencoder](https://huggingface.co/hivetrace/gliner-guard-uniencoder).
+
+# 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("lmo3/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("lmo3/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(
+    "lmo3/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(
+    "lmo3/gliner2-large-v1-onnx",
+    precision="fp16"
+)
+```
+
+## Models
+
+Pre-exported ONNX models:
+
+| Model | HuggingFace |
+|-------|-------------|
+| gliner2-large-v1 | [lmo3/gliner2-large-v1-onnx](https://huggingface.co/lmo3/gliner2-large-v1-onnx) |
+| gliner2-multi-v1 | [lmo3/gliner2-multi-v1-onnx](https://huggingface.co/lmo3/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": 384,
+  "vocab_size": 256000
+}

gliner2_config.json

@@ -0,0 +1,35 @@
+{
+  "max_width": 12,
+  "special_tokens": {
+    "[SEP_STRUCT]": 256000,
+    "[SEP_TEXT]": 256001,
+    "[P]": 256002,
+    "[C]": 256003,
+    "[E]": 256004,
+    "[R]": 256005,
+    "[L]": 256006,
+    "[EXAMPLE]": 256007,
+    "[OUTPUT]": 256008,
+    "[DESCRIPTION]": 256009
+  },
+  "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"
+    },
+    "int8": {
+      "encoder": "onnx/encoder_int8.onnx",
+      "classifier": "onnx/classifier_int8.onnx",
+      "span_rep": "onnx/span_rep_int8.onnx",
+      "count_embed": "onnx/count_embed_int8.onnx"
+    }
+  }
+}

onnx/classifier.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed76f308554e94b2bb389d5f186d1ad378018861bee09dd99746f5fd176b081
+size 1186506

onnx/classifier_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bdabb37377f8dba8570646170e63e1008bb7b2c0360bbd339e4434a8c5f4cee
+size 593983

onnx/classifier_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61133458388b60bf588d158e7296b9363744f507cfefbcf13906ab497a49c1c7
+size 301840

onnx/count_embed.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e89cfa6ae760074b2ffb125760015faf18e439e2f3268008936444ca695589
+size 258304

onnx/count_embed.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4181175c786beb679b49e82d9b33d5330d626815cffc4061a419d0b595079f
+size 6777344

onnx/count_embed_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1713826842118907088757e1bc855c3b8aa1ec5cab8e4fa2d6b7d65398431c6f
+size 271137

onnx/count_embed_fp16.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bd47a1e6e46cc0fa3895061530e9344cede56c5d22bc39556d121cc5c263a4d
+size 3375104

onnx/count_embed_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064854549090722f40714c4b6f5b57dda3e61047b56244ab95ace95791014fd9
+size 1955108

onnx/encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99b8fc5e95eed3348e87d0a0b7a213c053c1cc730f86fc8f37c9950360bbee1c
+size 562502073

onnx/encoder_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4f7e40609b46952c71f620d658d033afc57e7541a329c630ef61148086f33c0
+size 281675442

onnx/encoder_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c251526d1fe502b5ce2c3a5be04d9421e1a1c6fee3e21beb9fef7f9da41599e
+size 141369019

onnx/span_rep.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950b357c9fcf9688854024b66cd9de96788ae5a5a94ffa4009b73067bdf09261
+size 16543168

onnx/span_rep_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa9671906b5f92cd508e1fd23ebfcaef23e6b30aa212cb29c7677922e92dc360
+size 8276589

onnx/span_rep_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2635e77cc3e65b353add9606078c875c498c01269d98fd310a028302e4a6d632
+size 4165286

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b71cf441ac63c636686a771c74758b9d5d42c1fbea57eecd63bc567774d9ccc9
+size 34365025

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<bos>",
+  "eos_token": "<eos>",
+  "extra_special_tokens": [
+    "[SEP_STRUCT]",
+    "[SEP_TEXT]",
+    "[P]",
+    "[C]",
+    "[E]",
+    "[R]",
+    "[L]",
+    "[EXAMPLE]",
+    "[OUTPUT]",
+    "[DESCRIPTION]"
+  ],
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sep_token": "<eos>",
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}