gte-small-onnx
gte-small-onnx is a leading small encoder model from thenlper/gte-small, packaged in ONNX format.
This encoder can be used to generate vector embeddings.
Model Description
- Developed by: thenlper
- Quantized by: llmware
- Model type: bert
- Parameters: 22 million
- Model Parent: thenlper/gte-base
- Language(s) (NLP): English
- License: Apache 2.0
- Uses: Prompt safety
- RAG Benchmark Accuracy Score: NA
- Quantization: int4
Model Card Contact
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for llmware/gte-small-onnx
Base model
thenlper/gte-small