metadata
license: apache-2.0
language:
- en
base_model:
- sentence-transformers/all-MiniLM-L6-v2
pipeline_tag: sentence-similarity
tags:
- bert
- int8
- dynamic
- sentence-transformers
all-MiniLM-L6-v2 (INT8, ONNX)
This repository contains an INT8-quantized version of all-MiniLM-L6-v2. The quantize dynamic quantization method was used for maximum cross-platform compatibility.
Based on the original model: https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2
Post-training INT8 quantization
Optimized for cross-platform compatibility
Suitable for embeddings, semantic search, and text classification
Note: This is a derivative work with quantization only.