Upload 12 files

.gitattributes

@@ -1,35 +1,36 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.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
-*.xz 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
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.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
+*.xz 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 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -1,3 +1,224 @@
 ---
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+base_model:
+- avemio/German-RAG-BGE-M3-TRIPLES-MERGED-HESSIAN-AI
+- Snowflake/snowflake-arctic-embed-l-v2.0
+base_model_relation: merge
+widget:
+- source_sentence: 'search_query: i love autotrain'
+  sentences:
+  - 'search_query: huggingface auto train'
+  - 'search_query: hugging face auto train'
+  - 'search_query: i love autotrain'
+pipeline_tag: sentence-similarity
+datasets:
+- avemio/German-RAG-EMBEDDING-TRIPLES-HESSIAN-AI
 license: mit
+language:
+- de
+- en
 ---
+
+# German-RAG-BGE-M3-MERGED-x-SNOWFLAKE-ARCTIC-HESSIAN-AI
+
+This is a merged [sentence-transformers](https://www.SBERT.net) model. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+Our [German-RAG-BGE-M3-MERGED Model](https://huggingface.co/avemio/German-RAG-BGE-M3-TRIPLES-MERGED-HESSIAN-AI/) was merged with [Snowflake/snowflake-arctic-embed-l-v2.0](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) to exceed performances from each Base-Model.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
+- **Maximum Sequence Length:** 8192 tokens
+- **Output Dimensionality:** 1024 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Evaluation MTEB-Tasks 
+
+### Classification
+- AmazonCounterfactualClassification
+- AmazonReviewsClassification
+- MassiveIntentClassification
+- MassiveScenarioClassification
+- MTOPDomainClassification
+- MTOPIntentClassification
+
+### Pair Classification
+- FalseFriendsGermanEnglish
+- PawsXPairClassification
+
+### Retrieval
+- GermanQuAD-Retrieval
+- GermanDPR
+
+### STS (Semantic Textual Similarity)
+- GermanSTSBenchmark
+
+#### Comparison between the Snowflake Arctic Model ([Snowflake](https://huggingface.co/BAAI/bge-m3)), our Merged Model ([Merged-BGE](https://huggingface.co/avemio/German-RAG-BGE-M3-TRIPLES-HESSIAN-AI)) and our Merged-BGE Model merged with [Snowflake/snowflake-arctic-embed-l-v2.0](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0)
+
+| TASK                                | Snowflake | Merged-BGE | Merged-Snowflake | German-RAG vs. Snowflake | Merged-Snowflake vs. Snowflake | Merged-Snowflake vs. Merged-BGE |
+|-------------------------------------|-----------|------------|------------------|--------------------|-------------------------------|---------------------------------|
+| AmazonCounterfactualClassification | 0.6587    | 0.7111     | **0.7152**           | 5.24%             | 5.65%                        | 0.41%                          |
+| AmazonReviewsClassification         | 0.3697    | 0.4571     | **0.4577**           | 8.74%             | 8.80%                        | 0.06%                          |
+| FalseFriendsGermanEnglish           | 0.5360    | 0.5338     | **0.5378**           | -0.22%            | 0.18%                        | 0.40%                          |
+| GermanQuAD-Retrieval                | 0.9423    | 0.9311     | **0.9456**           | -1.12%            | 0.33%                        | 1.45%                          |
+| GermanSTSBenchmark                  | 0.7499    | 0.8218     | **0.8558**           | 7.19%             | 10.59%                       | 3.40%                          |
+| MassiveIntentClassification         | 0.6778    | 0.6522     | **0.6826**           | -2.56%            | 0.48%                        | 3.04%                          |
+| MassiveScenarioClassification       | 0.7375    | 0.7381     | **0.7494**           | 0.06%             | 1.19%                        | 1.13%                          |
+| GermanDPR                           | 0.8367    | 0.8159     | **0.8330**           | -2.08%            | -0.37%                       | 1.71%                          |
+| MTOPDomainClassification            | 0.9080    | 0.9139     | **0.9259**           | 0.59%             | 1.79%                        | 1.20%                          |
+| MTOPIntentClassification            | 0.6675    | 0.6684     | **0.7143**           | 0.09%             | 4.68%                        | 4.59%                          |
+| PawsXPairClassification             | 0.5887    | 0.5710     | **0.5803**           | -1.77%            | -0.84%                       | 0.93%                          |
+
+#### Comparison between Original Base-Model ([BGE-M3](https://huggingface.co/BAAI/bge-m3)), Merged Model with Base-Model ([Merged-BGE](https://huggingface.co/avemio/German-RAG-BGE-M3-TRIPLES-MERGED-HESSIAN-AI/)) and our Merged-BGE Model merged with [Snowflake/snowflake-arctic-embed-l-v2.0](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0)
+
+| TASK                                | [BGE-M3](https://huggingface.co/BAAI/bge-m3)   | Merged-BGE | [Merged-Snowflake](https://huggingface.co/avemio/German-RAG-BGE-M3-MERGED-x-SNOWFLAKE-ARCTIC-HESSIAN-AI/) | Merged-BGE vs. BGE | Merged-Snowflake vs. BGE | Merged-Snowflake vs. Merged-BGE |
+|-------------------------------------|-------|------------|------------------|--------------------|--------------------------|---------------------------------|
+| AmazonCounterfactualClassification | 0.6908 | 0.7111     | **0.7152**           | 2.94%             | 3.53%                   | 0.58%                          |
+| AmazonReviewsClassification         | **0.4634** | 0.4571     | 0.4577           | -1.36%            | -1.23%                  | 0.13%                          |
+| FalseFriendsGermanEnglish           | 0.5343 | 0.5338     | **0.5378**           | -0.09%            | 0.66%                   | 0.75%                          |
+| GermanQuAD-Retrieval                | 0.9444 | 0.9311     | **0.9456**           | -1.41%            | 0.13%                   | 1.56%                          |
+| GermanSTSBenchmark                  | 0.8079 | 0.8218     | **0.8558**           | 1.72%             | 5.93%                   | 4.14%                          |
+| MassiveIntentClassification         | 0.6575 | 0.6522     | **0.6826**           | -0.81%            | 3.82%                   | 4.66%                          |
+| MassiveScenarioClassification       | 0.7355 | 0.7381     | **0.7494**           | 0.35%             | 1.89%                   | 1.53%                          |
+| GermanDPR                           | 0.8265 | 0.8159     | **0.8330**           | -1.28%            | 0.79%                   | 2.10%                          |
+| MTOPDomainClassification            | 0.9121 | 0.9139     | **0.9259**           | 0.20%             | 1.52%                   | 1.31%                          |
+| MTOPIntentClassification            | 0.6808 | 0.6684     | **0.7143**           | -1.82%            | 4.91%                   | 6.87%                          |
+| PawsXPairClassification             | 0.5678 | 0.5710     | **0.5803**           | 0.56%             | 2.18%                   | 1.63%                          |
+
+## Evaluation on German-RAG-EMBEDDING-BENCHMARK
+
+Accuracy is calculated by evaluating if the relevant context is the highest ranking embedding of the whole context array.
+See Eval-Dataset and Evaluation Code [here](https://huggingface.co/datasets/avemio/German-RAG-EMBEDDING-BENCHMARK)
+
+| Model Name                                       | Accuracy  |
+|-------------------------------------------------|-----------|
+| [bge-m3](https://huggingface.co/BAAI/bge-m3  )                                     | 0.8806    |
+| [UAE-Large-V1](https://huggingface.co/WhereIsAI/UAE-Large-V1)                            | 0.8393    |
+| [German-RAG-BGE-M3-TRIPLES-HESSIAN-AI](https://huggingface.co/avemio/German-RAG-BGE-M3-TRIPLES-HESSIAN-AI)             | 0.8857    |
+| [German-RAG-BGE-M3-TRIPLES-MERGED-HESSIAN-AI](https://huggingface.co/avemio/German-RAG-BGE-M3-TRIPLES-MERGED-HESSIAN-AI)      | **0.8866** |
+| [German-RAG-BGE-M3-MERGED-x-SNOWFLAKE-ARCTIC-HESSIAN-AI](https://huggingface.co/avemio/German-RAG-BGE-M3-MERGED-x-SNOWFLAKE-ARCTIC-HESSIAN-AI)   | **0.8866** |
+| [German-RAG-UAE-LARGE-V1-TRIPLES-HESSIAN-AI](https://huggingface.co/avemio/German-RAG-UAE-LARGE-V1-TRIPLES-HESSIAN-AI)       | 0.8763    |
+| [German-RAG-UAE-LARGE-V1-TRIPLES-MERGED-HESSIAN-AI](https://huggingface.co/avemio/German-RAG-UAE-LARGE-V1-TRIPLES-MERGED-HESSIAN-AI)   | 0.8771    |
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("avemio/German-RAG-BGE-M3-MERGED-x-SNOWFLAKE-ARCTIC-HESSIAN-AI")
+# Run inference
+sentences = [
+    'The weather is lovely today.',
+    "It's so sunny outside!",
+    'He drove to the stadium.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.2.1
+- Transformers: 4.44.2
+- PyTorch: 2.4.1+cu121
+- Accelerate: 0.34.2
+- Datasets: 3.0.1
+- Tokenizers: 0.19.1
+
+## Citation
+
+```
+@misc{bge-m3,
+      title={BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation}, 
+      author={Jianlv Chen and Shitao Xiao and Peitian Zhang and Kun Luo and Defu Lian and Zheng Liu},
+      year={2024},
+      eprint={2402.03216},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```
+
+
+## The German-RAG AI Team
+[Marcel Rosiak](https://de.linkedin.com/in/marcel-rosiak)
+[Soumya Paul](https://de.linkedin.com/in/soumya-paul-1636a68a)
+[Siavash Mollaebrahim](https://de.linkedin.com/in/siavash-mollaebrahim-4084b5153?trk=people-guest_people_search-card)
+[Zain ul Haq](https://de.linkedin.com/in/zain-ul-haq-31ba35196)

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/content/FlagEmbedding/mixed_embedder",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.2.1",
+    "transformers": "4.44.2",
+    "pytorch": "2.5.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f25cd89132ad134f3159e8146e7138ccf4f6cd70aefd638b7544f8f74de4fac
+size 2271064456

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "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 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
+size 17083053

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 8192,
+  "model_max_length": 8192,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}