|
--- |
|
library_name: sentence-transformers |
|
pipeline_tag: sentence-similarity |
|
tags: |
|
- sentence-transformers |
|
- sentence-similarity |
|
- feature-extraction |
|
license: mit |
|
datasets: |
|
- avemio/German-RAG-EMBEDDING-TRIPLES-HESSIAN-AI |
|
language: |
|
- de |
|
- en |
|
base_model: |
|
- avemio/German-RAG-UAE-LARGE-V1-TRIPLES-HESSIAN-AI |
|
- WhereIsAI/UAE-Large-V1 |
|
base_model_relation: merge |
|
--- |
|
|
|
# German-RAG-UAE-LARGE-V1-TRIPLES-MERGED-HESSIAN-AI |
|
|
|
This is a [sentence-transformers](https://www.SBERT.net) model trained on this [Dataset](https://huggingface.co/datasets/avemio/German-RAG-Embedding-Triples-Hessian-AI) with roughly 300k Triple-Samples. 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. |
|
It was merged with the Base-Model [WhereIsAI/UAE-Large-V1](https://huggingface.co/WhereIsAI/UAE-Large-V1) again to maintain performance on other languages again. |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
- **Model Type:** Sentence Transformer |
|
<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) --> |
|
- **Maximum Sequence Length:** 512 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': 512, 'do_lower_case': False}) with Transformer model: BertModel |
|
(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 |
|
|
|
| TASK | [UAE](https://huggingface.co/WhereIsAI/UAE-Large-V1/) | [German-RAG-UAE](https://huggingface.co/avemio/German-RAG-UAE-LARGE-V1-TRIPLES-HESSIAN-AI/) | Merged-UAE | German-RAG vs. UAE | Merged vs. UAE | |
|
|-------------------------------------|-------|----------|------------|--------------|----------------| |
|
| AmazonCounterfactualClassification | **0.5650** | 0.5449 | 0.5401 | -2.01% | -2.48% | |
|
| AmazonReviewsClassification | 0.2738 | 0.2745 | **0.2782** | 0.08% | 0.44% | |
|
| FalseFriendsGermanEnglish | **0.4808** | 0.4777 | 0.4703 | -0.32% | -1.05% | |
|
| GermanQuAD-Retrieval | 0.7811 | 0.8353 | **0.8628** | 5.42% | 8.18% | |
|
| GermanSTSBenchmark | 0.6421 | 0.6568 | **0.6754** | 1.47% | 3.33% | |
|
| MassiveIntentClassification | **0.5139** | 0.4884 | 0.4714 | -2.55% | -4.25% | |
|
| MassiveScenarioClassification | 0.6062 | 0.5837 | **0.6111** | -2.25% | 0.49% | |
|
| GermanDPR | 0.6750 | 0.7210 | **0.7507** | 4.60% | 7.57% | |
|
| MTOPDomainClassification | 0.7625 | 0.7450 | **0.7686** | -1.75% | 0.61% | |
|
| MTOPIntentClassification | **0.4994** | 0.4516 | 0.4413 | -4.77% | -5.80% | |
|
| PawsXPairClassification | **0.5452** | 0.5077 | 0.5162 | -3.76% | -2.90% | |
|
|
|
|
|
## 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-digital/UAE-Large-V1_Triples_Merged_with_base") |
|
# 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: 2.5.0+cu121 |
|
- Accelerate: 0.34.2 |
|
- Datasets: 2.19.0 |
|
- Tokenizers: 0.19.1 |
|
|
|
## Citation |
|
|
|
``` |
|
@article{li2023angle, |
|
title={AnglE-optimized Text Embeddings}, |
|
author={Li, Xianming and Li, Jing}, |
|
journal={arXiv preprint arXiv:2309.12871}, |
|
year={2023} |
|
} |
|
``` |
|
|
|
|
|
|
|
## 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) |
|
|
