← Back to models
BGE-M3
embedder
Embed text in over 100 languages into one 1024-dimensional space, with inputs up to 8192 tokens.
antfly inference pull BAAI/bge-m3Technical Specs
- Architecture
- XLM-RoBERTa
- Parameters
- 568M
- Dimensions
- 1024
multilingual
Usage
Pull the model
antfly inference pull BAAI/bge-m3Start Antfly Inference
# With Antfly standalone (Antfly Inference enabled by default)
antfly standalone
# Or run Antfly Inference on its own, listening on 127.0.0.1:8090
antfly inference runUse in configuration
{
"embedders": {
"local": {
"provider": "antfly",
"model": "BAAI/bge-m3"
}
}
}