Upload semantic highlighter source model files (#1)

- Add semantic highlighter model files with LFS for large files (38f51c459824d4553a9b5aca2a937ea8d8aae6b3)
- Add YAML metadata to model card (8ccc65f98244c72339627748a78fd5307d7f6267)
- Remove Usage section from README (4f35bdd227a07a5cb63bcfea18ce203d5bf44960)


Co-authored-by: Junqiu Lei <[email protected]>

.gitattributes

@@ -33,3 +33,4 @@ 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
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,29 @@
 ---
+language: en
 license: apache-2.0
+library_name: transformers
+tags:
+- opensearch
+- semantic-search
+- highlighting
+- sentence-highlighter
+- bert
+- text-classification
+- pytorch
+pipeline_tag: text-classification
 ---
+
+# opensearch-semantic-highlighter
+
+## Overview
+
+The OpenSearch semantic highlighter is a trained classifier that takes a document and query as input and returns a binary score for each sentence in the document indicating its relevance to the query. 
+
+## License
+
+This project is licensed under the [Apache v2.0 License](https://github.com/opensearch-project/neural-search/blob/main/LICENSE).
+
+
+## Copyright
+
+Copyright OpenSearch Contributors. See [NOTICE](https://github.com/opensearch-project/neural-search/blob/main/NOTICE) for details.

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertTaggerForSentenceExtraction"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae65ebbec6562c9badc6ae4bd5be5d1b55536ec840658c1d2821d0c6258b7146
+size 437958648

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "model_max_length": 512}