Upload model

.gitattributes

@@ -32,3 +32,4 @@ 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 +1,36 @@
+
+---
+license: apache-2.0
+library_name: span-marker
+tags:
+- span-marker
+- token-classification
+- ner
+- named-entity-recognition
+pipeline_tag: token-classification
+---
+
+# SpanMarker for Named Entity Recognition
+
+This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model that can be used for Named Entity Recognition. In particular, this SpanMarker model uses [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) as the underlying encoder. 
+
+## Usage
+
+To use this model for inference, first install the `span_marker` library:
+
+```bash
+pip install span_marker
+```
+
+You can then run inference with this model like so:
+
+```python
+from span_marker import SpanMarkerModel
+
+# Download from the 🤗 Hub
+model = SpanMarkerModel.from_pretrained("span_marker_model_name")
+# Run inference
+entities = model.predict("Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic to Paris.")
+```
+
+See the [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) repository for documentation and additional information on this library.

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<end>": 250003,
+  "<start>": 250002
+}

config.json

@@ -0,0 +1,230 @@
+{
+  "_name_or_path": "models\\span_marker_xlm_roberta_base_fewnerd_fine_super_2\\checkpoint-final",
+  "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": "O",
+      "1": "art-broadcastprogram",
+      "2": "art-film",
+      "3": "art-music",
+      "4": "art-other",
+      "5": "art-painting",
+      "6": "art-writtenart",
+      "7": "building-airport",
+      "8": "building-hospital",
+      "9": "building-hotel",
+      "10": "building-library",
+      "11": "building-other",
+      "12": "building-restaurant",
+      "13": "building-sportsfacility",
+      "14": "building-theater",
+      "15": "event-attack/battle/war/militaryconflict",
+      "16": "event-disaster",
+      "17": "event-election",
+      "18": "event-other",
+      "19": "event-protest",
+      "20": "event-sportsevent",
+      "21": "location-GPE",
+      "22": "location-bodiesofwater",
+      "23": "location-island",
+      "24": "location-mountain",
+      "25": "location-other",
+      "26": "location-park",
+      "27": "location-road/railway/highway/transit",
+      "28": "organization-company",
+      "29": "organization-education",
+      "30": "organization-government/governmentagency",
+      "31": "organization-media/newspaper",
+      "32": "organization-other",
+      "33": "organization-politicalparty",
+      "34": "organization-religion",
+      "35": "organization-showorganization",
+      "36": "organization-sportsleague",
+      "37": "organization-sportsteam",
+      "38": "other-astronomything",
+      "39": "other-award",
+      "40": "other-biologything",
+      "41": "other-chemicalthing",
+      "42": "other-currency",
+      "43": "other-disease",
+      "44": "other-educationaldegree",
+      "45": "other-god",
+      "46": "other-language",
+      "47": "other-law",
+      "48": "other-livingthing",
+      "49": "other-medical",
+      "50": "person-actor",
+      "51": "person-artist/author",
+      "52": "person-athlete",
+      "53": "person-director",
+      "54": "person-other",
+      "55": "person-politician",
+      "56": "person-scholar",
+      "57": "person-soldier",
+      "58": "product-airplane",
+      "59": "product-car",
+      "60": "product-food",
+      "61": "product-game",
+      "62": "product-other",
+      "63": "product-ship",
+      "64": "product-software",
+      "65": "product-train",
+      "66": "product-weapon"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "O": 0,
+      "art-broadcastprogram": 1,
+      "art-film": 2,
+      "art-music": 3,
+      "art-other": 4,
+      "art-painting": 5,
+      "art-writtenart": 6,
+      "building-airport": 7,
+      "building-hospital": 8,
+      "building-hotel": 9,
+      "building-library": 10,
+      "building-other": 11,
+      "building-restaurant": 12,
+      "building-sportsfacility": 13,
+      "building-theater": 14,
+      "event-attack/battle/war/militaryconflict": 15,
+      "event-disaster": 16,
+      "event-election": 17,
+      "event-other": 18,
+      "event-protest": 19,
+      "event-sportsevent": 20,
+      "location-GPE": 21,
+      "location-bodiesofwater": 22,
+      "location-island": 23,
+      "location-mountain": 24,
+      "location-other": 25,
+      "location-park": 26,
+      "location-road/railway/highway/transit": 27,
+      "organization-company": 28,
+      "organization-education": 29,
+      "organization-government/governmentagency": 30,
+      "organization-media/newspaper": 31,
+      "organization-other": 32,
+      "organization-politicalparty": 33,
+      "organization-religion": 34,
+      "organization-showorganization": 35,
+      "organization-sportsleague": 36,
+      "organization-sportsteam": 37,
+      "other-astronomything": 38,
+      "other-award": 39,
+      "other-biologything": 40,
+      "other-chemicalthing": 41,
+      "other-currency": 42,
+      "other-disease": 43,
+      "other-educationaldegree": 44,
+      "other-god": 45,
+      "other-language": 46,
+      "other-law": 47,
+      "other-livingthing": 48,
+      "other-medical": 49,
+      "person-actor": 50,
+      "person-artist/author": 51,
+      "person-athlete": 52,
+      "person-director": 53,
+      "person-other": 54,
+      "person-politician": 55,
+      "person-scholar": 56,
+      "person-soldier": 57,
+      "product-airplane": 58,
+      "product-car": 59,
+      "product-food": 60,
+      "product-game": 61,
+      "product-other": 62,
+      "product-ship": 63,
+      "product-software": 64,
+      "product-train": 65,
+      "product-weapon": 66
+    },
+    "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": "4.28.1",
+    "type_vocab_size": 1,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 250004
+  },
+  "entity_max_length": 8,
+  "marker_max_length": 128,
+  "max_next_context": null,
+  "max_prev_context": null,
+  "model_max_length": 256,
+  "model_max_length_default": 512,
+  "model_type": "span-marker",
+  "span_marker_version": "1.1.2.dev",
+  "torch_dtype": "float32",
+  "trained_with_document_context": false,
+  "transformers_version": "4.28.1",
+  "vocab_size": 250004
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60fe4f5f65948af6c809d5da6a3337475d071a4ea4320f7cd3843b1bf0989d1a
+size 1112663221

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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 sha256:7becf84dcb8c923f94254aff98d6e2f21190c901a95f5f4ec1059aa70a1215d0
+size 17083026

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": true,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}