Sentence Similarity
Transformers
Safetensors
sentence-transformers
llama
feature-extraction
custom_code
text-embeddings-inference
Instructions to use facebook/drama-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/drama-1b with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("facebook/drama-1b", trust_remote_code=True) model = AutoModel.from_pretrained("facebook/drama-1b", trust_remote_code=True) - sentence-transformers
How to use facebook/drama-1b with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("facebook/drama-1b", trust_remote_code=True) sentences = [ "هذا شخص سعيد", "هذا كلب سعيد", "هذا شخص سعيد جدا", "اليوم هو يوم مشمس" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
"corresponidng"
#2
by deleted - opened
README.md
CHANGED
|
@@ -91,7 +91,7 @@ It demonstrates strong performance in both English and multilingual retrieval ta
|
|
| 91 |
<img src="evaluation.png" style="width:800px;">
|
| 92 |
</p>
|
| 93 |
|
| 94 |
-
`drama-1b` released in this page is
|
| 95 |
|
| 96 |
## Supported Languages
|
| 97 |
DRAMA-1B was initialized from [Llama3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) (which was originally pruned from [Llama3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B)). During retriever training, training data covered the following 20 languages (sorted alphabetically):
|
|
|
|
| 91 |
<img src="evaluation.png" style="width:800px;">
|
| 92 |
</p>
|
| 93 |
|
| 94 |
+
`drama-1b` released in this page is corresponding to the line DRAMA-1B with 1B non-embedding parrameters.
|
| 95 |
|
| 96 |
## Supported Languages
|
| 97 |
DRAMA-1B was initialized from [Llama3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) (which was originally pruned from [Llama3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B)). During retriever training, training data covered the following 20 languages (sorted alphabetically):
|