Upload model

README.md

@@ -0,0 +1,37 @@
+
+---
+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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) 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>": 30523,
+  "<start>": 30522
+}

config.json

@@ -0,0 +1,419 @@
+{
+  "_name_or_path": "models\\span_marker_bert_base_uncased_cross_ner\\checkpoint-final",
+  "architectures": [
+    "SpanMarkerModel"
+  ],
+  "encoder": {
+    "_name_or_path": "bert-base-uncased",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "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": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "O",
+      "1": "B-academicjournal",
+      "2": "I-academicjournal",
+      "3": "B-album",
+      "4": "I-album",
+      "5": "B-algorithm",
+      "6": "I-algorithm",
+      "7": "B-astronomicalobject",
+      "8": "I-astronomicalobject",
+      "9": "B-award",
+      "10": "I-award",
+      "11": "B-band",
+      "12": "I-band",
+      "13": "B-book",
+      "14": "I-book",
+      "15": "B-chemicalcompound",
+      "16": "I-chemicalcompound",
+      "17": "B-chemicalelement",
+      "18": "I-chemicalelement",
+      "19": "B-conference",
+      "20": "I-conference",
+      "21": "B-country",
+      "22": "I-country",
+      "23": "B-discipline",
+      "24": "I-discipline",
+      "25": "B-election",
+      "26": "I-election",
+      "27": "B-enzyme",
+      "28": "I-enzyme",
+      "29": "B-event",
+      "30": "I-event",
+      "31": "B-field",
+      "32": "I-field",
+      "33": "B-literarygenre",
+      "34": "I-literarygenre",
+      "35": "B-location",
+      "36": "I-location",
+      "37": "B-magazine",
+      "38": "I-magazine",
+      "39": "B-metrics",
+      "40": "I-metrics",
+      "41": "B-misc",
+      "42": "I-misc",
+      "43": "B-musicalartist",
+      "44": "I-musicalartist",
+      "45": "B-musicalinstrument",
+      "46": "I-musicalinstrument",
+      "47": "B-musicgenre",
+      "48": "I-musicgenre",
+      "49": "B-organisation",
+      "50": "I-organisation",
+      "51": "B-person",
+      "52": "I-person",
+      "53": "B-poem",
+      "54": "I-poem",
+      "55": "B-politicalparty",
+      "56": "I-politicalparty",
+      "57": "B-politician",
+      "58": "I-politician",
+      "59": "B-product",
+      "60": "I-product",
+      "61": "B-programlang",
+      "62": "I-programlang",
+      "63": "B-protein",
+      "64": "I-protein",
+      "65": "B-researcher",
+      "66": "I-researcher",
+      "67": "B-scientist",
+      "68": "I-scientist",
+      "69": "B-song",
+      "70": "I-song",
+      "71": "B-task",
+      "72": "I-task",
+      "73": "B-theory",
+      "74": "I-theory",
+      "75": "B-university",
+      "76": "I-university",
+      "77": "B-writer",
+      "78": "I-writer"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "B-academicjournal": 1,
+      "B-album": 3,
+      "B-algorithm": 5,
+      "B-astronomicalobject": 7,
+      "B-award": 9,
+      "B-band": 11,
+      "B-book": 13,
+      "B-chemicalcompound": 15,
+      "B-chemicalelement": 17,
+      "B-conference": 19,
+      "B-country": 21,
+      "B-discipline": 23,
+      "B-election": 25,
+      "B-enzyme": 27,
+      "B-event": 29,
+      "B-field": 31,
+      "B-literarygenre": 33,
+      "B-location": 35,
+      "B-magazine": 37,
+      "B-metrics": 39,
+      "B-misc": 41,
+      "B-musicalartist": 43,
+      "B-musicalinstrument": 45,
+      "B-musicgenre": 47,
+      "B-organisation": 49,
+      "B-person": 51,
+      "B-poem": 53,
+      "B-politicalparty": 55,
+      "B-politician": 57,
+      "B-product": 59,
+      "B-programlang": 61,
+      "B-protein": 63,
+      "B-researcher": 65,
+      "B-scientist": 67,
+      "B-song": 69,
+      "B-task": 71,
+      "B-theory": 73,
+      "B-university": 75,
+      "B-writer": 77,
+      "I-academicjournal": 2,
+      "I-album": 4,
+      "I-algorithm": 6,
+      "I-astronomicalobject": 8,
+      "I-award": 10,
+      "I-band": 12,
+      "I-book": 14,
+      "I-chemicalcompound": 16,
+      "I-chemicalelement": 18,
+      "I-conference": 20,
+      "I-country": 22,
+      "I-discipline": 24,
+      "I-election": 26,
+      "I-enzyme": 28,
+      "I-event": 30,
+      "I-field": 32,
+      "I-literarygenre": 34,
+      "I-location": 36,
+      "I-magazine": 38,
+      "I-metrics": 40,
+      "I-misc": 42,
+      "I-musicalartist": 44,
+      "I-musicalinstrument": 46,
+      "I-musicgenre": 48,
+      "I-organisation": 50,
+      "I-person": 52,
+      "I-poem": 54,
+      "I-politicalparty": 56,
+      "I-politician": 58,
+      "I-product": 60,
+      "I-programlang": 62,
+      "I-protein": 64,
+      "I-researcher": 66,
+      "I-scientist": 68,
+      "I-song": 70,
+      "I-task": 72,
+      "I-theory": 74,
+      "I-university": 76,
+      "I-writer": 78,
+      "O": 0
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "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_scores": false,
+    "pad_token_id": 0,
+    "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": "4.31.0",
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30524
+  },
+  "entity_max_length": 8,
+  "id2label": {
+    "0": "O",
+    "1": "academicjournal",
+    "2": "album",
+    "3": "algorithm",
+    "4": "astronomicalobject",
+    "5": "award",
+    "6": "band",
+    "7": "book",
+    "8": "chemicalcompound",
+    "9": "chemicalelement",
+    "10": "conference",
+    "11": "country",
+    "12": "discipline",
+    "13": "election",
+    "14": "enzyme",
+    "15": "event",
+    "16": "field",
+    "17": "literarygenre",
+    "18": "location",
+    "19": "magazine",
+    "20": "metrics",
+    "21": "misc",
+    "22": "musicalartist",
+    "23": "musicalinstrument",
+    "24": "musicgenre",
+    "25": "organisation",
+    "26": "person",
+    "27": "poem",
+    "28": "politicalparty",
+    "29": "politician",
+    "30": "product",
+    "31": "programlang",
+    "32": "protein",
+    "33": "researcher",
+    "34": "scientist",
+    "35": "song",
+    "36": "task",
+    "37": "theory",
+    "38": "university",
+    "39": "writer"
+  },
+  "id2reduced_id": {
+    "0": 0,
+    "1": 1,
+    "2": 1,
+    "3": 2,
+    "4": 2,
+    "5": 3,
+    "6": 3,
+    "7": 4,
+    "8": 4,
+    "9": 5,
+    "10": 5,
+    "11": 6,
+    "12": 6,
+    "13": 7,
+    "14": 7,
+    "15": 8,
+    "16": 8,
+    "17": 9,
+    "18": 9,
+    "19": 10,
+    "20": 10,
+    "21": 11,
+    "22": 11,
+    "23": 12,
+    "24": 12,
+    "25": 13,
+    "26": 13,
+    "27": 14,
+    "28": 14,
+    "29": 15,
+    "30": 15,
+    "31": 16,
+    "32": 16,
+    "33": 17,
+    "34": 17,
+    "35": 18,
+    "36": 18,
+    "37": 19,
+    "38": 19,
+    "39": 20,
+    "40": 20,
+    "41": 21,
+    "42": 21,
+    "43": 22,
+    "44": 22,
+    "45": 23,
+    "46": 23,
+    "47": 24,
+    "48": 24,
+    "49": 25,
+    "50": 25,
+    "51": 26,
+    "52": 26,
+    "53": 27,
+    "54": 27,
+    "55": 28,
+    "56": 28,
+    "57": 29,
+    "58": 29,
+    "59": 30,
+    "60": 30,
+    "61": 31,
+    "62": 31,
+    "63": 32,
+    "64": 32,
+    "65": 33,
+    "66": 33,
+    "67": 34,
+    "68": 34,
+    "69": 35,
+    "70": 35,
+    "71": 36,
+    "72": 36,
+    "73": 37,
+    "74": 37,
+    "75": 38,
+    "76": 38,
+    "77": 39,
+    "78": 39
+  },
+  "label2id": {
+    "O": 0,
+    "academicjournal": 1,
+    "album": 2,
+    "algorithm": 3,
+    "astronomicalobject": 4,
+    "award": 5,
+    "band": 6,
+    "book": 7,
+    "chemicalcompound": 8,
+    "chemicalelement": 9,
+    "conference": 10,
+    "country": 11,
+    "discipline": 12,
+    "election": 13,
+    "enzyme": 14,
+    "event": 15,
+    "field": 16,
+    "literarygenre": 17,
+    "location": 18,
+    "magazine": 19,
+    "metrics": 20,
+    "misc": 21,
+    "musicalartist": 22,
+    "musicalinstrument": 23,
+    "musicgenre": 24,
+    "organisation": 25,
+    "person": 26,
+    "poem": 27,
+    "politicalparty": 28,
+    "politician": 29,
+    "product": 30,
+    "programlang": 31,
+    "protein": 32,
+    "researcher": 33,
+    "scientist": 34,
+    "song": 35,
+    "task": 36,
+    "theory": 37,
+    "university": 38,
+    "writer": 39
+  },
+  "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": "1.2.5.dev",
+  "torch_dtype": "float32",
+  "trained_with_document_context": false,
+  "transformers_version": "4.31.0",
+  "vocab_size": 30524
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7a48865c82987b9328a7aba643ab571999c30331750ab1f3698d5d26fa1f95
+size 438247153

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": true,
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}