from sentence_transformers import SentenceTransformer
model = SentenceTransformer("Bharatdeep-H/qwen3-jailbreaking-embeddings")
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]
qwen3-jailbreaking-embeddings (merged)
This is Qwen/Qwen3-Embedding-0.6B fine-tuned with LoRA on nihabilal/clean-jailbreak-prompts and merged into the base weights.
It’s a self-contained SentenceTransformer checkpoint (no PEFT required).
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Bharatdeep-H/qwen3-jailbreaking-embeddings") 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]