Update README.md
Browse files
README.md
CHANGED
|
@@ -1622,8 +1622,8 @@ language:
|
|
| 1622 |
# bge-small-en-v1.5-quant
|
| 1623 |
|
| 1624 |
<div>
|
| 1625 |
-
<img src="https://huggingface.co/zeroshot/bge-small-en-v1.5-quant/resolve/main/latency.png" alt="latency" width="
|
| 1626 |
-
<img src="https://huggingface.co/zeroshot/bge-small-en-v1.5-quant/resolve/main/throughput.png" alt="throughput" width="
|
| 1627 |
</div>
|
| 1628 |
|
| 1629 |
This is the quantized (INT8) ONNX variant of the [bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) embeddings model created with [DeepSparse Optimum](https://github.com/neuralmagic/optimum-deepsparse) for ONNX export/inference and Neural Magic's [Sparsify](https://github.com/neuralmagic/sparsify) for one-shot quantization.
|
|
|
|
| 1622 |
# bge-small-en-v1.5-quant
|
| 1623 |
|
| 1624 |
<div>
|
| 1625 |
+
<img src="https://huggingface.co/zeroshot/bge-small-en-v1.5-quant/resolve/main/latency.png" alt="latency" width="330" style="display:inline-block; margin-right:10px;"/>
|
| 1626 |
+
<img src="https://huggingface.co/zeroshot/bge-small-en-v1.5-quant/resolve/main/throughput.png" alt="throughput" width="330" style="display:inline-block;"/>
|
| 1627 |
</div>
|
| 1628 |
|
| 1629 |
This is the quantized (INT8) ONNX variant of the [bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) embeddings model created with [DeepSparse Optimum](https://github.com/neuralmagic/optimum-deepsparse) for ONNX export/inference and Neural Magic's [Sparsify](https://github.com/neuralmagic/sparsify) for one-shot quantization.
|