initial commit

LICENSE

@@ -0,0 +1,22 @@
+MIT License
+
+Copyright (c) 2023 Philip May, Deutsche Telekom AG
+Copyright (c) 2022 deepset GmbH
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,3 +1,30 @@
 ---
+pipeline_tag: sentence-similarity
+language:
+  - de
+tags:
+- sentence-transformers
+- sentence-similarity
+- transformers
+- setfit
+- onnx
 license: mit
+datasets:
+  - deutsche-telekom/ger-backtrans-paraphrase
 ---
+
+# German BERT large paraphrase cosine
+This is a [sentence-transformers](https://www.SBERT.net) model.
+It maps sentences & paragraphs (text) into a 1024 dimensional dense vector space.
+The model is intended to be used together with [SetFit](https://github.com/huggingface/setfit)
+to improve German few-shot text classification.
+
+This is the ONNX-Version of [deutsche-telekom/gbert-large-paraphrase-cosine](https://huggingface.co/deutsche-telekom/gbert-large-paraphrase-cosine)
+
+
+## Licensing
+Copyright (c) 2023 [Philip May](https://may.la/), [Deutsche Telekom AG](https://www.telekom.com/)\
+Copyright (c) 2022 [deepset GmbH](https://www.deepset.ai/)
+Licensed under the **MIT License** (the "License"); you may not use this file except in compliance with the License.
+You may obtain a copy of the License by reviewing the file
+[LICENSE](https://huggingface.co/deutsche-telekom/gbert-large-paraphrase-cosine/blob/main/LICENSE) in the repository.

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "deutsche-telekom/gbert-large-paraphrase-cosine",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e5ec2e21d9665a52c6fc5add7e23116cbc2253acb86de96ebc9e5bde698a26
+size 1339229961

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 +1,16 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}