Auto Upload

.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

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false
+}

README.md

@@ -0,0 +1,78 @@
+---
+license: cc-by-nc-4.0
+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
+---
+
+# 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 |
+
+## Evaluation results
+| Epoch | top_1 | top_3 | top_5 | top_10 | top_25 |
+| ----- | ----- | ----- | ----- | ----- | ----- |
+| 0 | 0.261 | 0.351 | 0.384 | 0.422 | 0.459 |
+
+## 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/Master).

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"
+  }
+}

lightning_logs/version_0/events.out.tfevents.1677190031.ki-jupyternotebook-8bdd

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c727d45b6b0325b5efb73f3a55c8789fc9ac2be1e5c5679ddfd4d01a08843dcf
+size 176579

lightning_logs/version_0/hparams.yaml

@@ -0,0 +1 @@
+{}

lightning_logs/version_1/events.out.tfevents.1677230323.ki-jupyternotebook-8bdd

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:268077638a7202d9a93684210d6e0dc8cca4f8a7b19331ab29cc1060a05f3f89
+size 20479

lightning_logs/version_1/hparams.yaml

@@ -0,0 +1 @@
+{}

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"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d6f373e938d295e60cafed14c4324134f3481cc6f54d575d9dab701339ec02
+size 1112245805

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>"
+}