How to use Linkup-Platform/linkup-sparseup-embed-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Linkup-Platform/linkup-sparseup-embed-v1", trust_remote_code=True)
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Linkup-Platform/linkup-sparseup-embed-v1", trust_remote_code=True) model = AutoModel.from_pretrained("Linkup-Platform/linkup-sparseup-embed-v1", trust_remote_code=True, device_map="auto")
How to use Linkup-Platform/linkup-sparseup-embed-v1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Linkup-Platform/linkup-sparseup-embed-v1", trust_remote_code=True) sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3]
https://huggingface.co/Linkup-Platform/linkup-sparseup-embed-v1/resolve/main/modules.json
hf download hf://Linkup-Platform/linkup-sparseup-embed-v1/modules.json
curl -L -o modules.json https://huggingface.co/Linkup-Platform/linkup-sparseup-embed-v1/resolve/main/modules.json
