Sentence Similarity
PyTorch
sentence-transformers
multimodal
embeddings
retrieval
image-text
audio-text
text-image-audio
tri-encoder
semantic-router
Eval Results (legacy)
Instructions to use llm-semantic-router/multi-modal-embed-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use llm-semantic-router/multi-modal-embed-large with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("llm-semantic-router/multi-modal-embed-large") 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
| { | |
| "types": { | |
| "text_0_Transformer": "sentence_transformers.base.modules.transformer.Transformer", | |
| "text_1_Pooling": "sentence_transformers.sentence_transformer.modules.pooling.Pooling", | |
| "text_2_Normalize": "sentence_transformers.sentence_transformer.modules.normalize.Normalize", | |
| "image_0_SiglipVisionTransformer": "modeling_multimodal_embed.SiglipVisionTransformer", | |
| "image_1_Pooling": "sentence_transformers.sentence_transformer.modules.pooling.Pooling", | |
| "image_2_Dense": "sentence_transformers.base.modules.dense.Dense", | |
| "image_3_Normalize": "sentence_transformers.sentence_transformer.modules.normalize.Normalize", | |
| "audio_0_WhisperEncoderTransformer": "modeling_multimodal_embed.WhisperEncoderTransformer", | |
| "audio_1_Pooling": "sentence_transformers.sentence_transformer.modules.pooling.Pooling", | |
| "audio_2_Dense": "sentence_transformers.base.modules.dense.Dense", | |
| "audio_3_Normalize": "sentence_transformers.sentence_transformer.modules.normalize.Normalize" | |
| }, | |
| "structure": { | |
| "text": [ | |
| "text_0_Transformer", | |
| "text_1_Pooling", | |
| "text_2_Normalize" | |
| ], | |
| "image": [ | |
| "image_0_SiglipVisionTransformer", | |
| "image_1_Pooling", | |
| "image_2_Dense", | |
| "image_3_Normalize" | |
| ], | |
| "audio": [ | |
| "audio_0_WhisperEncoderTransformer", | |
| "audio_1_Pooling", | |
| "audio_2_Dense", | |
| "audio_3_Normalize" | |
| ] | |
| }, | |
| "parameters": { | |
| "default_route": "text", | |
| "allow_empty_key": true, | |
| "route_mappings": {} | |
| } | |
| } |