ANEForge: Python for direct computation on the Apple Neural Engine
Paper • 2606.17090 • Published • 3
How to use aneforge/all-MiniLM-L6-v2 with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("aneforge/all-MiniLM-L6-v2")
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]An unmodified duplicate of sentence-transformers/all-MiniLM-L6-v2, tagged for use with
ANEForge so the weights load and run directly on the
Apple Neural Engine (no CoreML). Weights are byte-identical to the source; see the original repo for
the model details. Licensed apache-2.0 from the source.
from aneforge.sentence_transformers import SentenceTransformer
model = SentenceTransformer("aneforge/all-MiniLM-L6-v2")
emb = model.encode(["Hello from the Neural Engine"], normalize_embeddings=True)
ANEForge compiles the model's graph into a single ANE program and streams the weights from this repo
via huggingface_hub. See the docs and the
paper.
Base model
nreimers/MiniLM-L6-H384-uncased