electroglyph commited on
Commit
a9259f7
·
verified ·
1 Parent(s): a17503a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -2
README.md CHANGED
@@ -95,8 +95,6 @@ I have added a linear quantization node before the `sentence_embedding` output s
95
 
96
  This is compatible with the [qdrant](https://github.com/qdrant/qdrant) uint8 datatype for collections.
97
 
98
- No benchmarks, but it in my limited testing it's exactly equivalent to the FP32 output of the uint8 quantized ONNX model.
99
-
100
  # Quantization method
101
 
102
  Linear quantization for the scale -.3 to 0.3, which is what sentence_embedding is normalized to.
 
95
 
96
  This is compatible with the [qdrant](https://github.com/qdrant/qdrant) uint8 datatype for collections.
97
 
 
 
98
  # Quantization method
99
 
100
  Linear quantization for the scale -.3 to 0.3, which is what sentence_embedding is normalized to.