Sentence Similarity
sentence-transformers
Safetensors
English
nvomniembed
text
image
video
audio
vidore
multimodal-embedding
Text-to-Video retrieval
Text-to-Audio retrieval
Visual Document Retrieval
feature-extraction
custom_code
Instructions to use nvidia/omni-embed-nemotron-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use nvidia/omni-embed-nemotron-3b with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("nvidia/omni-embed-nemotron-3b", trust_remote_code=True) sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Tom Aarsen commited on
Commit ·
68bb46c
1
Parent(s): 1d1c442
Move 'message_format' into 'modality_config' under 'message' -> 'format'
Browse files
sentence_bert_config.json
CHANGED
|
@@ -19,11 +19,11 @@
|
|
| 19 |
},
|
| 20 |
"message": {
|
| 21 |
"method": "forward",
|
| 22 |
-
"method_output_name": ["hidden_states", -1]
|
|
|
|
| 23 |
}
|
| 24 |
},
|
| 25 |
"module_output_name": "token_embeddings",
|
| 26 |
-
"message_format": "structured",
|
| 27 |
"unpad_inputs": false,
|
| 28 |
"processing_kwargs": {
|
| 29 |
"chat_template": {
|
|
|
|
| 19 |
},
|
| 20 |
"message": {
|
| 21 |
"method": "forward",
|
| 22 |
+
"method_output_name": ["hidden_states", -1],
|
| 23 |
+
"format": "structured"
|
| 24 |
}
|
| 25 |
},
|
| 26 |
"module_output_name": "token_embeddings",
|
|
|
|
| 27 |
"unpad_inputs": false,
|
| 28 |
"processing_kwargs": {
|
| 29 |
"chat_template": {
|