Add new SentenceTransformer model
#1
by
tomaarsen
HF Staff
- opened
- 1_Pooling/config.json +10 -0
- README.md +26 -10
- config_sentence_transformers.json +14 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
1_Pooling/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"word_embedding_dimension": 1024,
|
| 3 |
+
"pooling_mode_cls_token": false,
|
| 4 |
+
"pooling_mode_mean_tokens": true,
|
| 5 |
+
"pooling_mode_max_tokens": false,
|
| 6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
| 7 |
+
"pooling_mode_weightedmean_tokens": false,
|
| 8 |
+
"pooling_mode_lasttoken": false,
|
| 9 |
+
"include_prompt": true
|
| 10 |
+
}
|
README.md
CHANGED
|
@@ -1,15 +1,16 @@
|
|
| 1 |
---
|
| 2 |
-
library_name: transformers
|
| 3 |
license: mit
|
| 4 |
datasets:
|
| 5 |
- clips/beir-nl-mmarco
|
| 6 |
- clips/beir-nl-hotpotqa
|
| 7 |
- clips/beir-nl-fever
|
| 8 |
-
language:
|
| 9 |
-
- nl
|
| 10 |
base_model:
|
| 11 |
- clips/e5-large-v2-t2t
|
| 12 |
pipeline_tag: sentence-similarity
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
# E5-large-v2-t2t-nl
|
|
@@ -60,14 +61,29 @@ print(scores.tolist())
|
|
| 60 |
Below is an example for usage with sentence_transformers.
|
| 61 |
```python
|
| 62 |
from sentence_transformers import SentenceTransformer
|
| 63 |
-
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
]
|
| 70 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
```
|
| 72 |
## Benchmark Evaluation
|
| 73 |
Results on MTEB-NL (models introduced in [our paper](https://arxiv.org/abs/2509.12340) and the best model per size category are highlighted in bold):
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: sentence-transformers
|
| 3 |
license: mit
|
| 4 |
datasets:
|
| 5 |
- clips/beir-nl-mmarco
|
| 6 |
- clips/beir-nl-hotpotqa
|
| 7 |
- clips/beir-nl-fever
|
| 8 |
+
language: nl
|
|
|
|
| 9 |
base_model:
|
| 10 |
- clips/e5-large-v2-t2t
|
| 11 |
pipeline_tag: sentence-similarity
|
| 12 |
+
tags:
|
| 13 |
+
- transformers
|
| 14 |
---
|
| 15 |
|
| 16 |
# E5-large-v2-t2t-nl
|
|
|
|
| 61 |
Below is an example for usage with sentence_transformers.
|
| 62 |
```python
|
| 63 |
from sentence_transformers import SentenceTransformer
|
| 64 |
+
|
| 65 |
+
# Load the model from Hugging Face
|
| 66 |
+
model = SentenceTransformer("clips/e5-large-v2-t2t-nl")
|
| 67 |
+
|
| 68 |
+
# Perform inference using encode_query/encode_document for retrieval,
|
| 69 |
+
# or encode_query for general purpose embeddings. Prompt prefixes
|
| 70 |
+
# are automatically added with these two methods.
|
| 71 |
+
queries = [
|
| 72 |
+
'hoeveel eiwitten moet een vrouw eten',
|
| 73 |
+
'top definieer',
|
| 74 |
+
]
|
| 75 |
+
documents = [
|
| 76 |
+
'Als algemene richtlijn geldt dat de gemiddelde eiwitbehoefte voor vrouwen van 19 tot 70 jaar volgens de CDC 46 gram per dag bedraagt. Maar, zoals je in deze tabel kunt zien, moet je dit verhogen als je zwanger bent of traint voor een marathon. Bekijk de onderstaande tabel om te zien hoeveel eiwitten je dagelijks zou moeten eten.',
|
| 77 |
+
'Definitie van top voor leerlingen Engels. : 1 het hoogste punt van een berg : de top van een berg. : 2 het hoogste niveau. : 3 een bijeenkomst of reeks bijeenkomsten tussen de leiders van twee of meer regeringen.',
|
| 78 |
]
|
| 79 |
+
query_embeddings = model.encode_query(queries)
|
| 80 |
+
document_embeddings = model.encode_document(documents)
|
| 81 |
+
print(query_embeddings.shape, document_embeddings.shape)
|
| 82 |
+
# (2, 1024) (2, 1024)
|
| 83 |
+
|
| 84 |
+
similarities = model.similarity(query_embeddings, document_embeddings)
|
| 85 |
+
# tensor([[0.7207, 0.2599],
|
| 86 |
+
# [0.2797, 0.6588]])
|
| 87 |
```
|
| 88 |
## Benchmark Evaluation
|
| 89 |
Results on MTEB-NL (models introduced in [our paper](https://arxiv.org/abs/2509.12340) and the best model per size category are highlighted in bold):
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "SentenceTransformer",
|
| 3 |
+
"__version__": {
|
| 4 |
+
"sentence_transformers": "5.1.0",
|
| 5 |
+
"transformers": "4.56.1",
|
| 6 |
+
"pytorch": "2.7.1+cu126"
|
| 7 |
+
},
|
| 8 |
+
"prompts": {
|
| 9 |
+
"query": "query: ",
|
| 10 |
+
"document": "passage: "
|
| 11 |
+
},
|
| 12 |
+
"default_prompt_name": null,
|
| 13 |
+
"similarity_fn_name": "cosine"
|
| 14 |
+
}
|
modules.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.models.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.models.Pooling"
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"idx": 2,
|
| 16 |
+
"name": "2",
|
| 17 |
+
"path": "2_Normalize",
|
| 18 |
+
"type": "sentence_transformers.models.Normalize"
|
| 19 |
+
}
|
| 20 |
+
]
|
sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|