Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,26 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- BAAI/bge-small-en-v1.5
|
| 7 |
+
tags:
|
| 8 |
+
- int8
|
| 9 |
+
- onnx
|
| 10 |
+
- bert
|
| 11 |
+
- sentence-similarity
|
| 12 |
+
- sentence-transformers
|
| 13 |
+
---
|
| 14 |
+
# bge-small-en-v1.5 (INT8, ONNX)
|
| 15 |
+
|
| 16 |
+
#### This repository contains an INT8-quantized version of bge-small-en-v1.5, converted to the ONNX format for efficient CPU inference.
|
| 17 |
+
|
| 18 |
+
#### Based on the original model: https://huggingface.co/BAAI/bge-small-en-v1.5
|
| 19 |
+
|
| 20 |
+
#### Post-training INT8 quantization
|
| 21 |
+
|
| 22 |
+
#### Optimized for fast and lightweight inference
|
| 23 |
+
|
| 24 |
+
#### Suitable for embeddings, semantic search, and text classification
|
| 25 |
+
|
| 26 |
+
*Note: This is a derivative work with format conversion and quantization only.*
|