Upload model

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,131 @@
+---
+library_name: span-marker
+tags:
+- span-marker
+- token-classification
+- ner
+- named-entity-recognition
+- generated_from_span_marker_trainer
+metrics:
+- precision
+- recall
+- f1
+widget: []
+pipeline_tag: token-classification
+---
+
+# SpanMarker
+
+This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model that can be used for Named Entity Recognition.
+
+## Model Details
+
+### Model Description
+- **Model Type:** SpanMarker
+<!-- - **Encoder:** [Unknown](https://huggingface.co/unknown) -->
+- **Maximum Sequence Length:** 512 tokens
+- **Maximum Entity Length:** 150 words
+<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Repository:** [SpanMarker on GitHub](https://github.com/tomaarsen/SpanMarkerNER)
+- **Thesis:** [SpanMarker For Named Entity Recognition](https://raw.githubusercontent.com/tomaarsen/SpanMarkerNER/main/thesis.pdf)
+
+## Uses
+
+### Direct Use for Inference
+
+```python
+from span_marker import SpanMarkerModel
+
+# Download from the 🤗 Hub
+model = SpanMarkerModel.from_pretrained("span_marker_model_id")
+# Run inference
+entities = model.predict("None")
+```
+
+### Downstream Use
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+```python
+from span_marker import SpanMarkerModel, Trainer
+
+# Download from the 🤗 Hub
+model = SpanMarkerModel.from_pretrained("span_marker_model_id")
+
+# Specify a Dataset with "tokens" and "ner_tag" columns
+dataset = load_dataset("conll2003") # For example CoNLL2003
+
+# Initialize a Trainer using the pretrained model & dataset
+trainer = Trainer(
+    model=model,
+    train_dataset=dataset["train"],
+    eval_dataset=dataset["validation"],
+)
+trainer.train()
+trainer.save_model("span_marker_model_id-finetuned")
+```
+</details>
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Framework Versions
+- Python: 3.10.12
+- SpanMarker: 1.5.0
+- Transformers: 4.35.2
+- PyTorch: 2.1.0+cu121
+- Datasets: 2.16.1
+- Tokenizers: 0.15.1
+
+## Citation
+
+### BibTeX
+```
+@software{Aarsen_SpanMarker,
+    author = {Aarsen, Tom},
+    license = {Apache-2.0},
+    title = {{SpanMarker for Named Entity Recognition}},
+    url = {https://github.com/tomaarsen/SpanMarkerNER}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,289 @@
+{
+  "_name_or_path": "/content/xlm-roberta-base-ar-mafat-ner",
+  "architectures": [
+    "SpanMarkerModel"
+  ],
+  "encoder": {
+    "_name_or_path": "xlm-roberta-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "XLMRobertaForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "U-ANG",
+      "1": "L-ANG",
+      "2": "B-ANG",
+      "3": "I-ANG",
+      "4": "U-DUC",
+      "5": "I-DUC",
+      "6": "L-DUC",
+      "7": "B-DUC",
+      "8": "I-EVE",
+      "9": "L-EVE",
+      "10": "B-EVE",
+      "11": "U-EVE",
+      "12": "L-FAC",
+      "13": "U-FAC",
+      "14": "I-FAC",
+      "15": "B-FAC",
+      "16": "L-GPE",
+      "17": "B-GPE",
+      "18": "I-GPE",
+      "19": "U-GPE",
+      "20": "U-INFORMAL",
+      "21": "I-INFORMAL",
+      "22": "L-INFORMAL",
+      "23": "B-INFORMAL",
+      "24": "U-LOC",
+      "25": "I-LOC",
+      "26": "L-LOC",
+      "27": "B-LOC",
+      "28": "I-MISC",
+      "29": "U-MISC",
+      "30": "B-MISC",
+      "31": "L-MISC",
+      "32": "O",
+      "33": "I-ORG",
+      "34": "L-ORG",
+      "35": "U-ORG",
+      "36": "B-ORG",
+      "37": "L-PER",
+      "38": "B-PER",
+      "39": "I-PER",
+      "40": "U-PER",
+      "41": "I-TIMEX",
+      "42": "L-TIMEX",
+      "43": "U-TIMEX",
+      "44": "B-TIMEX",
+      "45": "U-TTL",
+      "46": "L-TTL",
+      "47": "B-TTL",
+      "48": "I-TTL",
+      "49": "B-WOA",
+      "50": "L-WOA",
+      "51": "U-WOA",
+      "52": "I-WOA"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "B-ANG": 2,
+      "B-DUC": 7,
+      "B-EVE": 10,
+      "B-FAC": 15,
+      "B-GPE": 17,
+      "B-INFORMAL": 23,
+      "B-LOC": 27,
+      "B-MISC": 30,
+      "B-ORG": 36,
+      "B-PER": 38,
+      "B-TIMEX": 44,
+      "B-TTL": 47,
+      "B-WOA": 49,
+      "I-ANG": 3,
+      "I-DUC": 5,
+      "I-EVE": 8,
+      "I-FAC": 14,
+      "I-GPE": 18,
+      "I-INFORMAL": 21,
+      "I-LOC": 25,
+      "I-MISC": 28,
+      "I-ORG": 33,
+      "I-PER": 39,
+      "I-TIMEX": 41,
+      "I-TTL": 48,
+      "I-WOA": 52,
+      "L-ANG": 1,
+      "L-DUC": 6,
+      "L-EVE": 9,
+      "L-FAC": 12,
+      "L-GPE": 16,
+      "L-INFORMAL": 22,
+      "L-LOC": 26,
+      "L-MISC": 31,
+      "L-ORG": 34,
+      "L-PER": 37,
+      "L-TIMEX": 42,
+      "L-TTL": 46,
+      "L-WOA": 50,
+      "O": 32,
+      "U-ANG": 0,
+      "U-DUC": 4,
+      "U-EVE": 11,
+      "U-FAC": 13,
+      "U-GPE": 19,
+      "U-INFORMAL": 20,
+      "U-LOC": 24,
+      "U-MISC": 29,
+      "U-ORG": 35,
+      "U-PER": 40,
+      "U-TIMEX": 43,
+      "U-TTL": 45,
+      "U-WOA": 51
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 514,
+    "min_length": 0,
+    "model_type": "xlm-roberta",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.36.2",
+    "type_vocab_size": 1,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 250008
+  },
+  "entity_max_length": 150,
+  "id2label": {
+    "0": "O",
+    "1": "ANG",
+    "2": "DUC",
+    "3": "EVE",
+    "4": "FAC",
+    "5": "GPE",
+    "6": "INFORMAL",
+    "7": "LOC",
+    "8": "MISC",
+    "9": "ORG",
+    "10": "PER",
+    "11": "TIMEX",
+    "12": "TTL",
+    "13": "WOA"
+  },
+  "id2reduced_id": {
+    "0": 1,
+    "1": 1,
+    "2": 1,
+    "3": 1,
+    "4": 2,
+    "5": 2,
+    "6": 2,
+    "7": 2,
+    "8": 3,
+    "9": 3,
+    "10": 3,
+    "11": 3,
+    "12": 4,
+    "13": 4,
+    "14": 4,
+    "15": 4,
+    "16": 5,
+    "17": 5,
+    "18": 5,
+    "19": 5,
+    "20": 6,
+    "21": 6,
+    "22": 6,
+    "23": 6,
+    "24": 7,
+    "25": 7,
+    "26": 7,
+    "27": 7,
+    "28": 8,
+    "29": 8,
+    "30": 8,
+    "31": 8,
+    "32": 0,
+    "33": 9,
+    "34": 9,
+    "35": 9,
+    "36": 9,
+    "37": 10,
+    "38": 10,
+    "39": 10,
+    "40": 10,
+    "41": 11,
+    "42": 11,
+    "43": 11,
+    "44": 11,
+    "45": 12,
+    "46": 12,
+    "47": 12,
+    "48": 12,
+    "49": 13,
+    "50": 13,
+    "51": 13,
+    "52": 13
+  },
+  "label2id": {
+    "ANG": 1,
+    "DUC": 2,
+    "EVE": 3,
+    "FAC": 4,
+    "GPE": 5,
+    "INFORMAL": 6,
+    "LOC": 7,
+    "MISC": 8,
+    "O": 0,
+    "ORG": 9,
+    "PER": 10,
+    "TIMEX": 11,
+    "TTL": 12,
+    "WOA": 13
+  },
+  "marker_max_length": 128,
+  "max_next_context": null,
+  "max_prev_context": null,
+  "model_max_length": null,
+  "model_max_length_default": 512,
+  "model_type": "span-marker",
+  "span_marker_version": "1.5.0",
+  "torch_dtype": "float32",
+  "trained_with_document_context": false,
+  "transformers_version": "4.35.2",
+  "vocab_size": 250008
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9268b25b46635a447205bcab9c84c40d47b4695d96e91c801b32b427cd881f41
+size 1112303344

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4744345123bc9dbf0daa1471ddf0d6b25a367b938235dcdbab1114b274a07887
+size 17083318

tokenizer_config.json

@@ -0,0 +1,71 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250002": {
+      "content": "<start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250003": {
+      "content": "<end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}