added more quantization models

mesolitica · Nov 12, 2020 · 9b64f83 · 9b64f83
1 parent d98013b
commit 9b64f83
Show file tree

Hide file tree

Showing 146 changed files with 10,557 additions and 36,749 deletions.
diff --git a/README-pypi.rst b/README-pypi.rst
@@ -101,6 +101,9 @@ Features
 -  **Zero-shot classification**
 
    Provide Zero-shot classification interface using Transformer-Bahasa to recognize texts without any labeled training data.
+-  **Hybrid 8-bit Quantization**
+
+   Provide hybrid 8-bit quantization for all models to reduce speed inference up to 2x and model size up to 4x.
 
 Pretrained Models
 ------------------

diff --git a/README.rst b/README.rst
@@ -123,7 +123,7 @@ Features
    Provide Zero-shot classification interface using Transformer-Bahasa to recognize texts without any labeled training data.
 -  **Hybrid 8-bit Quantization**
 
-   Provide hybrid 8-bit quantization for all models to speed inference by 2x and reduce model size by 4x.
+   Provide hybrid 8-bit quantization for all models to reduce speed inference up to 2x and model size up to 4x.
 
 Pretrained Models
 ------------------

diff --git a/docs/README.rst b/docs/README.rst
@@ -121,6 +121,9 @@ Features
 -  **Zero-shot classification**
 
    Provide Zero-shot classification interface using Transformer-Bahasa to recognize texts without any labeled training data.
+-  **Hybrid 8-bit Quantization**
+
+   Provide hybrid 8-bit quantization for all models to reduce speed inference up to 2x and model size up to 4x.
 
 Pretrained Models
 ------------------