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: 3.10.8
+- SpanMarker: 1.5.0
+- Transformers: 4.28.0
+- PyTorch: 1.13.1+cu117
+- Datasets: 2.14.4
+- Tokenizers: 0.13.3
+
+## 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>": 50266,
+  "<start>": 50265
+}

config.json

@@ -0,0 +1,229 @@
+{
+  "_name_or_path": "/root/controversies-ops/models/span_marker_generic-ner-v1_fewnerd_fine_super/checkpoint-final",
+  "architectures": [
+    "SpanMarkerModel"
+  ],
+  "encoder": {
+    "_name_or_path": "numind/generic-entity_recognition-v1",
+    "add_cross_attention": false,
+    "architectures": [
+      "RobertaModel"
+    ],
+    "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": "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_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": "float32",
+    "torchscript": false,
+    "transformers_version": "4.28.0",
+    "type_vocab_size": 1,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50267
+  },
+  "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": "1.5.0",
+  "torch_dtype": "float32",
+  "trained_with_document_context": false,
+  "transformers_version": "4.28.0",
+  "vocab_size": 50267
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d884bbeb474f472d0c729cb07c27b97e7ac948ae75e6014eda04003fa37d95db
+size 499071157

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_prefix_space": true,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}