Upload 12 files

.gitattributes

@@ -1,35 +1,36 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+models_comparison.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,95 @@
 ---
 license: apache-2.0
+language:
+- multilingual
+library_name: gliner
+datasets:
+- urchade/pile-mistral-v0.1
+pipeline_tag: token-classification
 ---
+
+# About
+
+GLiNER is a Named Entity Recognition (NER) model capable of identifying any entity type using a bidirectional transformer encoder (BERT-like). It provides a practical alternative to traditional NER models, which are limited to predefined entities, and Large Language Models (LLMs) that, despite their flexibility, are costly and large for resource-constrained scenarios.
+
+
+## Links
+
+* Paper: https://arxiv.org/abs/2311.08526
+* Repository: https://github.com/urchade/GLiNER
+
+
+## Installation
+To use this model, you must install the GLiNER Python library:
+```
+!pip install gliner -U
+```
+
+## Usage
+Once you've downloaded the GLiNER library, you can import the GLiNER class. You can then load this model using `GLiNER.from_pretrained` and predict entities with `predict_entities`.
+
+```python
+from gliner import GLiNER
+
+model = GLiNER.from_pretrained("gliner-community/gliner_large-v2.5", load_tokenizer=True)
+
+text = """
+Cristiano Ronaldo dos Santos Aveiro (Portuguese pronunciation: [kɾiʃˈtjɐnu ʁɔˈnaldu]; born 5 February 1985) is a Portuguese professional footballer who plays as a forward for and captains both Saudi Pro League club Al Nassr and the Portugal national team. Widely regarded as one of the greatest players of all time, Ronaldo has won five Ballon d'Or awards,[note 3] a record three UEFA Men's Player of the Year Awards, and four European Golden Shoes, the most by a European player. He has won 33 trophies in his career, including seven league titles, five UEFA Champions Leagues, the UEFA European Championship and the UEFA Nations League. Ronaldo holds the records for most appearances (183), goals (140) and assists (42) in the Champions League, goals in the European Championship (14), international goals (128) and international appearances (205). He is one of the few players to have made over 1,200 professional career appearances, the most by an outfield player, and has scored over 850 official senior career goals for club and country, making him the top goalscorer of all time.
+"""
+
+labels = ["person", "award", "date", "competitions", "teams"]
+
+entities = model.predict_entities(text, labels)
+
+for entity in entities:
+    print(entity["text"], "=>", entity["label"])
+```
+
+```
+Cristiano Ronaldo dos Santos Aveiro => person
+5 February 1985 => date
+Al Nassr => teams
+Portugal national team => teams
+Ballon d'Or => award
+UEFA Men's Player of the Year Awards => award
+European Golden Shoes => award
+UEFA Champions Leagues => competitions
+UEFA European Championship => competitions
+UEFA Nations League => competitions
+Champions League => competitions
+European Championship => competitions
+```
+
+## Named Entity Recognition benchmark result
+Below is a comparison of results between previous versions of the model and the current one:
+![Models performance](models_comparison.png)
+
+## Other available models
+
+| Release | Model Name | # of Parameters | Language | License |
+| - | - | - | - | - |
+| v0 | [urchade/gliner_base](https://huggingface.co/urchade/gliner_base)<br>[urchade/gliner_multi](https://huggingface.co/urchade/gliner_multi) | 209M<br>209M | English<br>Multilingual | cc-by-nc-4.0 |
+| v1 | [urchade/gliner_small-v1](https://huggingface.co/urchade/gliner_small-v1)<br>[urchade/gliner_medium-v1](https://huggingface.co/urchade/gliner_medium-v1)<br>[urchade/gliner_large-v1](https://huggingface.co/urchade/gliner_large-v1) | 166M<br>209M<br>459M | English <br> English <br> English | cc-by-nc-4.0 |
+| v2 | [urchade/gliner_small-v2](https://huggingface.co/urchade/gliner_small-v2)<br>[urchade/gliner_medium-v2](https://huggingface.co/urchade/gliner_medium-v2)<br>[urchade/gliner_large-v2](https://huggingface.co/urchade/gliner_large-v2) | 166M<br>209M<br>459M |  English <br> English <br> English | apache-2.0 |
+| v2.1 | [urchade/gliner_small-v2.1](https://huggingface.co/urchade/gliner_small-v2.1)<br>[urchade/gliner_medium-v2.1](https://huggingface.co/urchade/gliner_medium-v2.1)<br>[urchade/gliner_large-v2.1](https://huggingface.co/urchade/gliner_large-v2.1) <br>[urchade/gliner_multi-v2.1](https://huggingface.co/urchade/gliner_multi-v2.1) | 166M<br>209M<br>459M<br>209M | English <br> English <br> English <br> Multilingual | apache-2.0 |
+
+
+## Model Authors
+The model authors are:
+* [Urchade Zaratiana](https://huggingface.co/urchade)
+* [Ihor Stepanov](https://huggingface.co/Ihor)
+* Nadi Tomeh
+* Pierre Holat
+* Thierry Charnois
+
+## Citation
+```bibtex
+@misc{zaratiana2023gliner,
+      title={GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer}, 
+      author={Urchade Zaratiana and Nadi Tomeh and Pierre Holat and Thierry Charnois},
+      year={2023},
+      eprint={2311.08526},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<<ENT>>": 128001,
+  "<<SEP>>": 128002,
+  "[MASK]": 128000
+}

gliner_config.json

@@ -0,0 +1,28 @@
+{
+  "class_token_index": 128001,
+  "dropout": 0.4,
+  "encoder_config": null,
+  "ent_token": "<<ENT>>",
+  "fine_tune": true,
+  "has_rnn": true,
+  "hidden_size": 768,
+  "label_smoothing": 0.0,
+  "loss_alpha": 0.8,
+  "loss_gamma": 0,
+  "loss_reduction": "sum",
+  "max_len": 768,
+  "max_neg_type_ratio": 1,
+  "max_types": 30,
+  "max_width": 12,
+  "model_name": "microsoft/deberta-v3-large",
+  "model_type": "gliner",
+  "name": "span level gliner",
+  "random_drop": true,
+  "sep_token": "<<SEP>>",
+  "shuffle_types": true,
+  "span_mode": "markerV0",
+  "subtoken_pooling": "first",
+  "transformers_version": "4.40.2",
+  "vocab_size": 128003,
+  "words_splitter_type": "whitespace"
+}

handler.py

@@ -0,0 +1,17 @@
+from gliner import GLiNER
+
+class EndpointHandler:
+    def __init__(self, path=""):
+        # Use the provided path for loading the model
+        self.model = GLiNER.from_pretrained(path)
+
+    def __call__(self, data):
+        try:
+            text = data.get("text", "")
+            labels = data.get("labels", [])
+            if not text or not labels:
+                return {"error": "Please provide 'text' and 'labels'"}
+            entities = self.model.predict(text, labels)
+            return {"entities": entities}
+        except Exception as e:
+            return {"error": str(e)}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a0f6f2109367a7157d7a0a00f8383d80ba232c1fd9c7fa88ee653011226c64
+size 1838129390

requirements.txt

@@ -0,0 +1,2 @@
+torch
+gliner

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,74 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<<ENT>>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128002": {
+      "content": "<<SEP>>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}