Update README.md
Browse files
README.md
CHANGED
|
@@ -15,13 +15,14 @@ license: apache-2.0
|
|
| 15 |
datasets:
|
| 16 |
- BlackKakapo/RoSTSC
|
| 17 |
base_model:
|
| 18 |
-
-
|
| 19 |
---
|
| 20 |
|
| 21 |
-
# 🔥 cupidon-
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
-
Don’t be shy — cupidon-base-ro is here to charm your embeddings into alignment 💘. Based on the solid foundations of `BlackKakapo/stsb-xlm-r-multilingual-ro` and lovingly fine-tuned on Romanian STS data, this model brings more than just good looks to the table.
|
| 24 |
-
Because in the end, true meaning isn’t just in the words... it's in how you embed them. 🧠💕
|
| 25 |
## Usage (Sentence-Transformers)
|
| 26 |
|
| 27 |
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
|
@@ -36,7 +37,7 @@ Then you can use the model like this:
|
|
| 36 |
from sentence_transformers import SentenceTransformer
|
| 37 |
sentences = ["This is an example sentence", "Each sentence is converted"]
|
| 38 |
|
| 39 |
-
model = SentenceTransformer('BlackKakapo/cupidon-
|
| 40 |
embeddings = model.encode(sentences)
|
| 41 |
print(embeddings)
|
| 42 |
```
|
|
@@ -60,8 +61,8 @@ def mean_pooling(model_output, attention_mask):
|
|
| 60 |
sentences = ['This is an example sentence', 'Each sentence is converted']
|
| 61 |
|
| 62 |
# Load model from HuggingFace Hub
|
| 63 |
-
tokenizer = AutoTokenizer.from_pretrained('BlackKakapo/cupidon-
|
| 64 |
-
model = AutoModel.from_pretrained('BlackKakapo/cupidon-
|
| 65 |
```
|
| 66 |
|
| 67 |
## License
|
|
@@ -70,8 +71,8 @@ This dataset is licensed under **Apache 2.0**.
|
|
| 70 |
## Citation
|
| 71 |
If you use BlackKakapo/cupidon-tiny-ro in your research, please cite this model as follows:
|
| 72 |
```
|
| 73 |
-
@misc{cupidon-
|
| 74 |
-
title={BlackKakapo/cupidon-
|
| 75 |
author={BlackKakapo},
|
| 76 |
year={2025},
|
| 77 |
}
|
|
|
|
| 15 |
datasets:
|
| 16 |
- BlackKakapo/RoSTSC
|
| 17 |
base_model:
|
| 18 |
+
- sentence-transformers-testing/stsb-bert-tiny-safetensors
|
| 19 |
---
|
| 20 |
|
| 21 |
+
# 🔥 cupidon-tiny-ro
|
| 22 |
+
|
| 23 |
+
Don’t let the name fool you — cupidon-tiny-ro may be small, but it hits right in the semantic feels 💘. Fine-tuned from `sentence-transformers-testing/stsb-bert-tiny-safetensors`, this [sentence-transformers](https://www.SBERT.net) model was trained with love (and Romanian data) to turn sentences into sharp, compact embeddings.
|
| 24 |
+
Perfect for tasks like semantic similarity, clustering, or search — and let’s be honest... sometimes, size doesn’t matter when you really know how to encode a sentence. 😉
|
| 25 |
|
|
|
|
|
|
|
| 26 |
## Usage (Sentence-Transformers)
|
| 27 |
|
| 28 |
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
|
|
|
| 37 |
from sentence_transformers import SentenceTransformer
|
| 38 |
sentences = ["This is an example sentence", "Each sentence is converted"]
|
| 39 |
|
| 40 |
+
model = SentenceTransformer('BlackKakapo/cupidon-tiny-ro')
|
| 41 |
embeddings = model.encode(sentences)
|
| 42 |
print(embeddings)
|
| 43 |
```
|
|
|
|
| 61 |
sentences = ['This is an example sentence', 'Each sentence is converted']
|
| 62 |
|
| 63 |
# Load model from HuggingFace Hub
|
| 64 |
+
tokenizer = AutoTokenizer.from_pretrained('BlackKakapo/cupidon-tiny-ro')
|
| 65 |
+
model = AutoModel.from_pretrained('BlackKakapo/cupidon-tiny-ro')
|
| 66 |
```
|
| 67 |
|
| 68 |
## License
|
|
|
|
| 71 |
## Citation
|
| 72 |
If you use BlackKakapo/cupidon-tiny-ro in your research, please cite this model as follows:
|
| 73 |
```
|
| 74 |
+
@misc{cupidon-tiny-ro,
|
| 75 |
+
title={BlackKakapo/cupidon-tiny-ro},
|
| 76 |
author={BlackKakapo},
|
| 77 |
year={2025},
|
| 78 |
}
|