avemio-digital commited on
Commit
4747db8
·
verified ·
1 Parent(s): 22ffea5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -13
README.md CHANGED
@@ -7,21 +7,21 @@ tags:
7
  - feature-extraction
8
  license: mit
9
  datasets:
10
- - avemio/GRAG-EMBEDDING-TRIPLES-HESSIAN-AI
11
  language:
12
  - de
13
  - en
14
  base_model:
15
- - avemio/GRAG-UAE-LARGE-V1-TRIPLES-HESSIAN-AI
16
  - WhereIsAI/UAE-Large-V1
17
  base_model_relation: merge
18
  ---
19
 
20
- <img src="https://www.grag.ai/wp-content/uploads/2024/12/GRAG-ICON-TO-WORDLOGO-Animation_Loop-small-ezgif.com-video-to-gif-converter.gif" alt="GRAG Logo" width="400" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
21
 
22
- # GRAG-UAE-LARGE-V1-TRIPLES-MERGED-HESSIAN-AI
23
 
24
- This is a [sentence-transformers](https://www.SBERT.net) model trained on this [Dataset](https://huggingface.co/datasets/avemio/GRAG-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.
25
  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.
26
 
27
  ## Model Details
@@ -73,7 +73,7 @@ SentenceTransformer(
73
  ### STS (Semantic Textual Similarity)
74
  - GermanSTSBenchmark
75
 
76
- | TASK | [UAE](https://huggingface.co/WhereIsAI/UAE-Large-V1/) | [GRAG-UAE](https://huggingface.co/avemio/GRAG-UAE-LARGE-V1-TRIPLES-HESSIAN-AI/) | Merged-UAE | GRAG vs. UAE | Merged vs. UAE |
77
  |-------------------------------------|-------|----------|------------|--------------|----------------|
78
  | AmazonCounterfactualClassification | **0.5650** | 0.5449 | 0.5401 | -2.01% | -2.48% |
79
  | AmazonReviewsClassification | 0.2738 | 0.2745 | **0.2782** | 0.08% | 0.44% |
@@ -88,20 +88,20 @@ SentenceTransformer(
88
  | PawsXPairClassification | **0.5452** | 0.5077 | 0.5162 | -3.76% | -2.90% |
89
 
90
 
91
- ## Evaluation on GRAG-EMBEDDING-BENCHMARK
92
 
93
  Accuracy is calculated by evaluating if the relevant context is the highest ranking embedding of the whole context array.
94
- See Eval-Dataset and Evaluation Code [here](https://huggingface.co/datasets/avemio/GRAG-EMBEDDING-BENCHMARK)
95
 
96
  | Model Name | Accuracy |
97
  |-------------------------------------------------|-----------|
98
  | [bge-m3](https://huggingface.co/BAAI/bge-m3 ) | 0.8806 |
99
  | [UAE-Large-V1](https://huggingface.co/WhereIsAI/UAE-Large-V1) | 0.8393 |
100
- | [GRAG-BGE-M3-TRIPLES-HESSIAN-AI](https://huggingface.co/avemio/GRAG-BGE-M3-TRIPLES-HESSIAN-AI) | 0.8857 |
101
- | [GRAG-BGE-M3-TRIPLES-MERGED-HESSIAN-AI](https://huggingface.co/avemio/GRAG-BGE-M3-TRIPLES-MERGED-HESSIAN-AI) | **0.8866** |
102
- | [GRAG-BGE-M3-MERGED-x-SNOWFLAKE-ARCTIC-HESSIAN-AI](https://huggingface.co/avemio/GRAG-BGE-M3-MERGED-x-SNOWFLAKE-ARCTIC-HESSIAN-AI) | **0.8866** |
103
- | [GRAG-UAE-LARGE-V1-TRIPLES-HESSIAN-AI](https://huggingface.co/avemio/GRAG-UAE-LARGE-V1-TRIPLES-HESSIAN-AI) | 0.8763 |
104
- | [GRAG-UAE-LARGE-V1-TRIPLES-MERGED-HESSIAN-AI](https://huggingface.co/avemio/GRAG-UAE-LARGE-V1-TRIPLES-MERGED-HESSIAN-AI) | 0.8771 |
105
 
106
 
107
  ## Usage
 
7
  - feature-extraction
8
  license: mit
9
  datasets:
10
+ - avemio/German-RAG-EMBEDDING-TRIPLES-HESSIAN-AI
11
  language:
12
  - de
13
  - en
14
  base_model:
15
+ - avemio/German-RAG-UAE-LARGE-V1-TRIPLES-HESSIAN-AI
16
  - WhereIsAI/UAE-Large-V1
17
  base_model_relation: merge
18
  ---
19
 
20
+ <img src="https://www.German-RAG.ai/wp-content/uploads/2024/12/German-RAG-ICON-TO-WORDLOGO-Animation_Loop-small-ezgif.com-video-to-gif-converter.gif" alt="German-RAG Logo" width="400" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
21
 
22
+ # German-RAG-UAE-LARGE-V1-TRIPLES-MERGED-HESSIAN-AI
23
 
24
+ 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.
25
  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.
26
 
27
  ## Model Details
 
73
  ### STS (Semantic Textual Similarity)
74
  - GermanSTSBenchmark
75
 
76
+ | 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 |
77
  |-------------------------------------|-------|----------|------------|--------------|----------------|
78
  | AmazonCounterfactualClassification | **0.5650** | 0.5449 | 0.5401 | -2.01% | -2.48% |
79
  | AmazonReviewsClassification | 0.2738 | 0.2745 | **0.2782** | 0.08% | 0.44% |
 
88
  | PawsXPairClassification | **0.5452** | 0.5077 | 0.5162 | -3.76% | -2.90% |
89
 
90
 
91
+ ## Evaluation on German-RAG-EMBEDDING-BENCHMARK
92
 
93
  Accuracy is calculated by evaluating if the relevant context is the highest ranking embedding of the whole context array.
94
+ See Eval-Dataset and Evaluation Code [here](https://huggingface.co/datasets/avemio/German-RAG-EMBEDDING-BENCHMARK)
95
 
96
  | Model Name | Accuracy |
97
  |-------------------------------------------------|-----------|
98
  | [bge-m3](https://huggingface.co/BAAI/bge-m3 ) | 0.8806 |
99
  | [UAE-Large-V1](https://huggingface.co/WhereIsAI/UAE-Large-V1) | 0.8393 |
100
+ | [German-RAG-BGE-M3-TRIPLES-HESSIAN-AI](https://huggingface.co/avemio/German-RAG-BGE-M3-TRIPLES-HESSIAN-AI) | 0.8857 |
101
+ | [German-RAG-BGE-M3-TRIPLES-MERGED-HESSIAN-AI](https://huggingface.co/avemio/German-RAG-BGE-M3-TRIPLES-MERGED-HESSIAN-AI) | **0.8866** |
102
+ | [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** |
103
+ | [German-RAG-UAE-LARGE-V1-TRIPLES-HESSIAN-AI](https://huggingface.co/avemio/German-RAG-UAE-LARGE-V1-TRIPLES-HESSIAN-AI) | 0.8763 |
104
+ | [German-RAG-UAE-LARGE-V1-TRIPLES-MERGED-HESSIAN-AI](https://huggingface.co/avemio/German-RAG-UAE-LARGE-V1-TRIPLES-MERGED-HESSIAN-AI) | 0.8771 |
105
 
106
 
107
  ## Usage