Upload 12 files

.gitattributes

@@ -25,7 +25,6 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
@@ -33,3 +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

.gitignore

@@ -0,0 +1,3 @@
+checkpoints/
+checkpoint-*/
+runs/

README.md

@@ -1 +1,105 @@
-convert pytorch model.bin from orginal repo : LLukas22/paraphrase-multilingual-mpnet-base-v2-embedding-all to safetensors
+---
+license: apache-2.0
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+- generated_from_trainer
+datasets:
+- squad
+- newsqa
+- LLukas22/cqadupstack
+- LLukas22/fiqa
+- LLukas22/scidocs
+- deepset/germanquad
+- LLukas22/nq
+language:
+- en
+- de
+---
+
+# paraphrase-multilingual-mpnet-base-v2-embedding-all
+
+This model is a fine-tuned version of [paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) on the following datasets: [squad](https://huggingface.co/datasets/squad), [newsqa](https://huggingface.co/datasets/newsqa), [LLukas22/cqadupstack](https://huggingface.co/datasets/LLukas22/cqadupstack), [LLukas22/fiqa](https://huggingface.co/datasets/LLukas22/fiqa), [LLukas22/scidocs](https://huggingface.co/datasets/LLukas22/scidocs), [deepset/germanquad](https://huggingface.co/datasets/deepset/germanquad), [LLukas22/nq](https://huggingface.co/datasets/LLukas22/nq).
+
+
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('LLukas22/paraphrase-multilingual-mpnet-base-v2-embedding-all')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+## Training hyperparameters
+The following hyperparameters were used during training:
+
+- learning_rate: 1E+00
+- per device batch size: 40
+- effective batch size: 120
+- seed: 42
+- optimizer: AdamW with betas (0.9,0.999) and eps 1E-08
+- weight decay: 2E-02
+- D-Adaptation: True
+- Warmup: True
+- number of epochs: 15
+- mixed_precision_training: bf16
+
+## Training results
+| Epoch | Train Loss | Validation Loss |
+| ----- | ---------- | --------------- |
+| 0 | 0.085 | 0.0625 |
+| 1 | 0.0598 | 0.0554 |
+| 2 | 0.0484 | 0.0518 |
+| 3 | 0.0405 | 0.0485 |
+| 4 | 0.0341 | 0.0463 |
+| 5 | 0.0287 | 0.0454 |
+| 6 | 0.0243 | 0.0445 |
+| 7 | 0.0207 | 0.0426 |
+| 8 | 0.0177 | 0.0424 |
+| 9 | 0.0153 | 0.0421 |
+| 10 | 0.0134 | 0.0417 |
+| 11 | 0.012 | 0.0411 |
+| 12 | 0.011 | 0.0414 |
+
+## Evaluation results
+| Epoch | top_1 | top_3 | top_5 | top_10 | top_25 |
+| ----- | ----- | ----- | ----- | ----- | ----- |
+| 0 | 0.261 | 0.351 | 0.384 | 0.422 | 0.459 |
+| 1 | 0.272 | 0.365 | 0.4 | 0.439 | 0.477 |
+| 2 | 0.276 | 0.37 | 0.404 | 0.443 | 0.481 |
+| 3 | 0.292 | 0.391 | 0.426 | 0.465 | 0.503 |
+| 4 | 0.295 | 0.395 | 0.431 | 0.47 | 0.51 |
+| 5 | 0.299 | 0.4 | 0.437 | 0.476 | 0.514 |
+| 6 | 0.306 | 0.404 | 0.44 | 0.478 | 0.515 |
+| 7 | 0.309 | 0.41 | 0.445 | 0.485 | 0.521 |
+| 8 | 0.31 | 0.411 | 0.448 | 0.487 | 0.524 |
+| 9 | 0.315 | 0.417 | 0.454 | 0.493 | 0.529 |
+| 10 | 0.319 | 0.42 | 0.457 | 0.495 | 0.53 |
+| 11 | 0.323 | 0.424 | 0.46 | 0.497 | 0.531 |
+| 12 | 0.324 | 0.427 | 0.464 | 0.501 | 0.536 |
+
+## Framework versions
+- Transformers: 4.25.1
+- PyTorch: 2.0.0.dev20230210+cu118
+- PyTorch Lightning: 1.8.6
+- Datasets: 2.7.1
+- Tokenizers: 0.13.1
+- Sentence Transformers: 2.2.2
+
+## Additional Information
+This model was trained as part of my Master's Thesis **'Evaluation of transformer based language models for use in service information systems'**. The source code is available on [Github](https://github.com/LLukas22/Retrieval-Augmented-QA).

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.25.1",
+    "pytorch": "2.0.0.dev20230210+cu118"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:969ed0dc7232598c6317c19adb43b2487629965c75c94cdfb5200d141b67083d
+size 556110788

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

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:b60b6b43406a48bf3638526314f3d232d97058bc93472ff2de930d43686fa441
+size 17082913

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "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,
+  "name_or_path": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}