trend commited on
UPD
Browse files
README.md
CHANGED
|
@@ -11,4 +11,17 @@ tags:
|
|
| 11 |
- tiny
|
| 12 |
- sentence-similarity
|
| 13 |
- sentence-transformers
|
| 14 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
- tiny
|
| 12 |
- sentence-similarity
|
| 13 |
- sentence-transformers
|
| 14 |
+
---
|
| 15 |
+
# RuBERT v2 Tiny (INT8, ONNX)
|
| 16 |
+
|
| 17 |
+
#### This repository contains an INT8-quantized version of RuBERT v2 Tiny, converted to the ONNX format for efficient CPU inference.
|
| 18 |
+
|
| 19 |
+
#### Based on the original model: https://huggingface.co/cointegrated/rubert-tiny2
|
| 20 |
+
|
| 21 |
+
#### Post-training INT8 quantization
|
| 22 |
+
|
| 23 |
+
#### Optimized for fast and lightweight inference
|
| 24 |
+
|
| 25 |
+
#### Suitable for embeddings, semantic search, and text classification
|
| 26 |
+
|
| 27 |
+
*Note: This is a derivative work with format conversion and quantization only.*
|