Upload model

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:** 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("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: 3.11.7
+- SpanMarker: 1.5.0
+- Transformers: 4.36.2
+- PyTorch: 2.2.1
+- Datasets: 2.16.1
+- Tokenizers: 0.15.0
+
+## 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>": 31103,
+  "<start>": 31102
+}

config.json

@@ -0,0 +1,207 @@
+{
+  "_name_or_path": "models/span-marker-ktzh-stazh/span-marker-ktzh-stazh/",
+  "architectures": [
+    "SpanMarkerModel"
+  ],
+  "encoder": {
+    "_name_or_path": "deepset/gelectra-large",
+    "add_cross_attention": false,
+    "architectures": [
+      "ElectraForPreTraining"
+    ],
+    "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,
+    "embedding_size": 1024,
+    "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,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "O",
+      "1": "B-LOC",
+      "2": "I-LOC",
+      "3": "B-LOCderiv",
+      "4": "I-LOCderiv",
+      "5": "B-LOCpart",
+      "6": "I-LOCpart",
+      "7": "B-ORG",
+      "8": "I-ORG",
+      "9": "B-ORGderiv",
+      "10": "I-ORGderiv",
+      "11": "B-ORGpart",
+      "12": "I-ORGpart",
+      "13": "B-OTH",
+      "14": "I-OTH",
+      "15": "B-OTHderiv",
+      "16": "I-OTHderiv",
+      "17": "B-OTHpart",
+      "18": "I-OTHpart",
+      "19": "B-PER",
+      "20": "I-PER",
+      "21": "B-PERderiv",
+      "22": "I-PERderiv",
+      "23": "B-PERpart",
+      "24": "I-PERpart"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "B-LOC": 1,
+      "B-LOCderiv": 3,
+      "B-LOCpart": 5,
+      "B-ORG": 7,
+      "B-ORGderiv": 9,
+      "B-ORGpart": 11,
+      "B-OTH": 13,
+      "B-OTHderiv": 15,
+      "B-OTHpart": 17,
+      "B-PER": 19,
+      "B-PERderiv": 21,
+      "B-PERpart": 23,
+      "I-LOC": 2,
+      "I-LOCderiv": 4,
+      "I-LOCpart": 6,
+      "I-ORG": 8,
+      "I-ORGderiv": 10,
+      "I-ORGpart": 12,
+      "I-OTH": 14,
+      "I-OTHderiv": 16,
+      "I-OTHpart": 18,
+      "I-PER": 20,
+      "I-PERderiv": 22,
+      "I-PERpart": 24,
+      "O": 0
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "electra",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "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,
+    "summary_activation": "gelu",
+    "summary_last_dropout": 0.1,
+    "summary_type": "first",
+    "summary_use_proj": true,
+    "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": 31104
+  },
+  "entity_max_length": 8,
+  "id2label": {
+    "0": "O",
+    "1": "LOC",
+    "2": "LOCderiv",
+    "3": "LOCpart",
+    "4": "ORG",
+    "5": "ORGderiv",
+    "6": "ORGpart",
+    "7": "OTH",
+    "8": "OTHderiv",
+    "9": "OTHpart",
+    "10": "PER",
+    "11": "PERderiv",
+    "12": "PERpart"
+  },
+  "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
+  },
+  "label2id": {
+    "LOC": 1,
+    "LOCderiv": 2,
+    "LOCpart": 3,
+    "O": 0,
+    "ORG": 4,
+    "ORGderiv": 5,
+    "ORGpart": 6,
+    "OTH": 7,
+    "OTHderiv": 8,
+    "OTHpart": 9,
+    "PER": 10,
+    "PERderiv": 11,
+    "PERpart": 12
+  },
+  "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": "1.2.4",
+  "torch_dtype": "float32",
+  "trained_with_document_context": false,
+  "transformers_version": "4.36.2",
+  "vocab_size": 31104
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f09d5a4bd2384587bf0dbef1daa3310de68b9cba7130571cbf28f84b9c5f74
+size 1338907540

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 +1,76 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31102": {
+      "content": "<start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31103": {
+      "content": "<end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "entity_max_length": 8,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}