Sentence Similarity
sentence-transformers
Safetensors
English
llava_next
multimodal-retrieval
embedding-model
custom_code
Instructions to use BAAI/BGE-VL-MLLM-S1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use BAAI/BGE-VL-MLLM-S1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("BAAI/BGE-VL-MLLM-S1", 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
Simplify processor_config.json for transformers v4.x compatibility
#4
by tomaarsen HF Staff - opened
Hello!
Pull Request overview
- Simplify processor_config.json for transformers v4.x compatibility
Details
When implementing https://huggingface.co/BAAI/BGE-VL-v1.5-zs, I noticed that the original Transformers v4.x code will get confused by the processor_config.json having an image_processor key. This PR removes that key again, which means this data is loaded from preprocessor_config.json instead, and now Transformers v4.x and v5+ should work. Apologies.
- Tom Aarsen
tomaarsen changed pull request status to open
JUNJIE99 changed pull request status to merged