Downloads · 30 days
20
36% of all-time downloads
all-mpnet-base-v2
aneforge/all-mpnet-base-v2
all-mpnet-base-v2 is a sentence similarity model from aneforge. Use it when you need a score for how close two texts are. It is set up for aneforge. The card lists the license as apache-2.0.
An unmodified duplicate of sentence-transformers/all-mpnet-base-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; s…
All-time downloads
55
Public
Parameters
109M
438 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors438 MB · 100%
Parameter types
How the weights are stored.
F32109M · 100%
Base models
Model card
From the Hugging Face model README
all-mpnet-base-v2 (ANEForge)
An unmodified duplicate of sentence-transformers/all-mpnet-base-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.
Use with ANEForge
# pip install "aneforge[models]"
from aneforge.sentence_transformers import SentenceTransformer
model = SentenceTransformer("aneforge/all-mpnet-base-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.
- Task
- Sentence Similarity
- Library
- aneforge
- Type
- mpnet
- License
- apache-2.0
- Created
- Aug 31, 2026
- Updated
- Aug 31, 2026