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-cased](https://huggingface.co/bert-base-cased) 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>": 28997,
+  "<start>": 28996
+}

config.json

@@ -0,0 +1,123 @@
+{
+  "_name_or_path": "models\\span_marker_bert_base_acronyms\\checkpoint-final",
+  "architectures": [
+    "SpanMarkerModel"
+  ],
+  "encoder": {
+    "_name_or_path": "bert-base-cased",
+    "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": "B-long",
+      "1": "B-short",
+      "2": "I-long",
+      "3": "I-short",
+      "4": "O"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "B-long": 0,
+      "B-short": 1,
+      "I-long": 2,
+      "I-short": 3,
+      "O": 4
+    },
+    "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": 28998
+  },
+  "entity_max_length": 8,
+  "id2label": {
+    "0": "O",
+    "1": "LONG",
+    "2": "SHORT"
+  },
+  "id2reduced_id": {
+    "0": 1,
+    "1": 2,
+    "2": 1,
+    "3": 2,
+    "4": 0
+  },
+  "label2id": {
+    "LONG": 1,
+    "O": 0,
+    "SHORT": 2
+  },
+  "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": 28998
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b60063b813ab8a8a15e8c15c7258685cd21fe2ca6a5e0e3d2f347140b33f747e
+size 433331825

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": false,
+  "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]"
+}