Ralfi Kier commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,6 @@ tags:
|
|
| 9 |
- embedding
|
| 10 |
- snowflake2_m_uint8
|
| 11 |
- snowflake
|
| 12 |
-
- transformers.js
|
| 13 |
license: apache-2.0
|
| 14 |
language:
|
| 15 |
- af
|
|
@@ -95,7 +94,7 @@ 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
|
| 99 |
|
| 100 |
# Quantization method
|
| 101 |
|
|
|
|
| 9 |
- embedding
|
| 10 |
- snowflake2_m_uint8
|
| 11 |
- snowflake
|
|
|
|
| 12 |
license: apache-2.0
|
| 13 |
language:
|
| 14 |
- af
|
|
|
|
| 94 |
|
| 95 |
This is compatible with the [qdrant](https://github.com/qdrant/qdrant) uint8 datatype for collections.
|
| 96 |
|
| 97 |
+
No benchmarks, but in my limited testing it's exactly equivalent to the FP32 output of the uint8 quantized ONNX model.
|
| 98 |
|
| 99 |
# Quantization method
|
| 100 |
|