bge-base-en-v1.5 โ CoreML (.mlpackage)
CoreML conversion of BAAI/bge-base-en-v1.5 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 |
config.json |
Model configuration |
Details
- Precision: FP16 (native ANE precision)
- Compute units:
.allโ CoreML schedules across ANE, GPU, and CPU - Input shapes: batch=1, seq_len=1..512 (flexible range)
- Embedding dimension: 768
Usage with cai
cai index --embed-backend swift --embed-model "rsvalerio/bge-base-en-v1.5-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
- Downloads last month
- 24
Model tree for rsvalerio/bge-base-en-v1.5-coreml
Base model
BAAI/bge-base-en-v1.5