Upload folder using huggingface_hub

README.md

@@ -9,6 +9,7 @@ tags:
 - embedding
 - snowflake2_m_uint8
 - snowflake
+- transformers.js
 license: apache-2.0
 language:
 - af
@@ -86,12 +87,6 @@ language:
 - yo
 - zh
 ---
-# NOTICE
-
-Currently benchmarking this, not sure how accurate it is yet. I'll be updating this.
-
-Update: Still testing, but this seems to be pretty close to where it should be. I might be able to improve it by 1-2%.
-
 # snowflake2_m_uint8
 
 This is a slightly modified version of the uint8 quantized ONNX model from https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v2.0
@@ -100,13 +95,11 @@ I have added a linear quantization node before the `sentence_embedding` output s
 
 This is compatible with the [qdrant](https://github.com/qdrant/qdrant) uint8 datatype for collections.
 
-No benchmarks, but in my limited testing it's exactly equivalent to the FP32 output of the uint8 quantized ONNX model.
+No benchmarks, but it in my limited testing it's exactly equivalent to the FP32 output of the uint8 quantized ONNX model.
 
 # Quantization method
 
-I ran every token through the unmodified uint8 ONNX model and logged the highest/lowest FP32 value seen in the output tensor.
-
-This approximate range is from -0.25 to 0.31.  I adjusted the zero point and quantized according to that scale directly in this ONNX model.
+Determined value range for FP32 tensor is -.31 to 0.31.  I quantized according to that scale directly in this ONNX model.
 
 Here's what the graph of the original output looks like:
 

snowflake2_m_uint8.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6eaaab219a11856e35ef2185adc6e8cb283b8fa6dc30ad8c8a5792ecd967a9a
+oid sha256:0ef454690f03d5b63dc333b2cb41611fa26d64a3efe7e0b21947cb953cce2a43
 size 310916367