Upload model

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,36 @@
+
+---
+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 usedfor Named Entity Recognition. In particular, this SpanMarker model uses [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) 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>": 250003,
+  "<start>": 250002
+}

config.json

@@ -0,0 +1,138 @@
+{
+  "_name_or_path": "models\\xrl-conll-512-128-8-full-context-3-pos-ids-max-num-spans-9\\checkpoint-final",
+  "architectures": [
+    "SpanMarkerModel"
+  ],
+  "encoder": {
+    "_name_or_path": "xlm-roberta-large",
+    "add_cross_attention": false,
+    "architectures": [
+      "XLMRobertaForMaskedLM"
+    ],
+    "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": 1024,
+    "id2label": {
+      "0": "O",
+      "1": "B-PER",
+      "2": "I-PER",
+      "3": "B-ORG",
+      "4": "I-ORG",
+      "5": "B-LOC",
+      "6": "I-LOC",
+      "7": "B-MISC",
+      "8": "I-MISC"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "B-LOC": 5,
+      "B-MISC": 7,
+      "B-ORG": 3,
+      "B-PER": 1,
+      "I-LOC": 6,
+      "I-MISC": 8,
+      "I-ORG": 4,
+      "I-PER": 2,
+      "O": 0
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 514,
+    "min_length": 0,
+    "model_type": "xlm-roberta",
+    "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_past": true,
+    "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": null,
+    "torchscript": false,
+    "transformers_version": "4.28.1",
+    "type_vocab_size": 1,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 250004
+  },
+  "entity_max_length": 8,
+  "id2label": {
+    "0": "O",
+    "1": "LOC",
+    "2": "MISC",
+    "3": "ORG",
+    "4": "PER"
+  },
+  "id2reduced_id": {
+    "0": 0,
+    "1": 4,
+    "2": 4,
+    "3": 3,
+    "4": 3,
+    "5": 1,
+    "6": 1,
+    "7": 2,
+    "8": 2
+  },
+  "label2id": {
+    "LOC": 1,
+    "MISC": 2,
+    "O": 0,
+    "ORG": 3,
+    "PER": 4
+  },
+  "marker_max_length": 128,
+  "max_next_context": null,
+  "max_prev_context": null,
+  "model_max_length": 512,
+  "model_max_length_default": 512,
+  "model_type": "span-marker",
+  "span_marker_version": "1.0.1",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "vocab_size": 250004
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ea569cf0a7a2834930099a0d64306ee6544fef82f2caccebaed328f0eeaa701
+size 2239745397

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7becf84dcb8c923f94254aff98d6e2f21190c901a95f5f4ec1059aa70a1215d0
+size 17083026

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": true,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}