Upload model

README.md

@@ -0,0 +1,133 @@
+---
+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/models/unknown) -->
+- **Maximum Sequence Length:** 256 tokens
+- **Maximum Entity Length:** 8 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("Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic to Paris.")
+```
+
+### 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: 3.9.16
+- SpanMarker: 1.3.1.dev
+- Transformers: 4.33.0
+- PyTorch: 2.0.1+cu118
+- Datasets: 2.14.0
+- Tokenizers: 0.13.2
+
+## 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.*
+-->

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<end>": 30523,
+  "<start>": 30522
+}

config.json

@@ -0,0 +1,179 @@
+{
+  "_name_or_path": "models\\tomaarsen\\span-marker-bert-base-uncased-sourcedata\\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-SMALL_MOLECULE",
+      "2": "I-SMALL_MOLECULE",
+      "3": "B-GENEPROD",
+      "4": "I-GENEPROD",
+      "5": "B-SUBCELLULAR",
+      "6": "I-SUBCELLULAR",
+      "7": "B-CELL_TYPE",
+      "8": "I-CELL_TYPE",
+      "9": "B-TISSUE",
+      "10": "I-TISSUE",
+      "11": "B-ORGANISM",
+      "12": "I-ORGANISM",
+      "13": "B-EXP_ASSAY",
+      "14": "I-EXP_ASSAY",
+      "15": "B-DISEASE",
+      "16": "I-DISEASE",
+      "17": "B-CELL_LINE",
+      "18": "I-CELL_LINE"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "B-CELL_LINE": 17,
+      "B-CELL_TYPE": 7,
+      "B-DISEASE": 15,
+      "B-EXP_ASSAY": 13,
+      "B-GENEPROD": 3,
+      "B-ORGANISM": 11,
+      "B-SMALL_MOLECULE": 1,
+      "B-SUBCELLULAR": 5,
+      "B-TISSUE": 9,
+      "I-CELL_LINE": 18,
+      "I-CELL_TYPE": 8,
+      "I-DISEASE": 16,
+      "I-EXP_ASSAY": 14,
+      "I-GENEPROD": 4,
+      "I-ORGANISM": 12,
+      "I-SMALL_MOLECULE": 2,
+      "I-SUBCELLULAR": 6,
+      "I-TISSUE": 10,
+      "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": "4.33.0",
+    "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": "CELL_LINE",
+    "2": "CELL_TYPE",
+    "3": "DISEASE",
+    "4": "EXP_ASSAY",
+    "5": "GENEPROD",
+    "6": "ORGANISM",
+    "7": "SMALL_MOLECULE",
+    "8": "SUBCELLULAR",
+    "9": "TISSUE"
+  },
+  "id2reduced_id": {
+    "0": 0,
+    "1": 7,
+    "2": 7,
+    "3": 5,
+    "4": 5,
+    "5": 8,
+    "6": 8,
+    "7": 2,
+    "8": 2,
+    "9": 9,
+    "10": 9,
+    "11": 6,
+    "12": 6,
+    "13": 4,
+    "14": 4,
+    "15": 3,
+    "16": 3,
+    "17": 1,
+    "18": 1
+  },
+  "label2id": {
+    "CELL_LINE": 1,
+    "CELL_TYPE": 2,
+    "DISEASE": 3,
+    "EXP_ASSAY": 4,
+    "GENEPROD": 5,
+    "O": 0,
+    "ORGANISM": 6,
+    "SMALL_MOLECULE": 7,
+    "SUBCELLULAR": 8,
+    "TISSUE": 9
+  },
+  "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": "1.3.1.dev",
+  "torch_dtype": "float32",
+  "trained_with_document_context": false,
+  "transformers_version": "4.33.0",
+  "vocab_size": 30524
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d1e3e40aa72cffd3f6fd38bb23a67b54ccdfda67e781ce4b717b111934267b
+size 438062705

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]"
+}