Downloads · 30 days
1
4% of all-time downloads
unixcoder-base-coreml
rsvalerio/unixcoder-base-coreml
unixcoder-base-coreml is a feature extraction model from rsvalerio. Use it when you need embeddings to search or compare text. It is set up for coremltools. The card lists the license as mit.
CoreML conversion of microsoft/unixcoder-base for native Apple Neural Engine / GPU inference on macOS and iOS.
All-time downloads
28
Public
Repo size
251 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin251 MB · 99%
At a glance
- Task
- Feature Extraction
- Library
- coremltools
- License
- mit
- Access
- Public
- Created
- Mar 25, 2026
- Updated
- Mar 25, 2026
- SHA
- 57ad2c95
Base models
Model card
From the Hugging Face model README
unixcoder-base — CoreML (.mlpackage)
CoreML conversion of microsoft/unixcoder-base for native Apple Neural Engine / GPU inference on macOS and iOS.
Files
| File | Description |
|---|---|
model.mlpackage/ | CoreML model (FP16, flexible shapes) |
tokenizer.json | HF fast tokenizer |
Details
- Architecture: RoBERTa (encoder-only, no token_type_ids)
- Precision: FP16 (native ANE precision)
- Compute units:
.all— CoreML schedules across ANE, GPU, and CPU - Input shapes: batch=1..512, seq_len=1..512 (flexible range)
- Embedding dimension: 768
Usage with cai
cai index --embed-backend swift --embed-model "rsvalerio/unixcoder-base-coreml"
The Swift backend downloads the .mlpackage from this repo, compiles it to .mlmodelc on first run (~30-60s), and caches the compiled model for subsequent runs.
Conversion
Converted using rsvalerio/models CI pipeline with coremltools.
pip install coremltools transformers torch
python convert.py
- Task
- Feature Extraction
- Library
- coremltools
- License
- mit
- Created
- Mar 25, 2026
- Updated
- Mar 25, 2026