Update README.md

README.md

@@ -1621,7 +1621,7 @@ language:
 
 # bge-small-en-v1.5-quant
 
-<img src="https://huggingface.co/zeroshot/bge-small-en-v1.5-quant/blob/main/OReUW-latency-of-bge-small-en-v1-5.png" alt="latency" width="600" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
+<img src="https://huggingface.co/zeroshot/bge-small-en-v1.5-quant/blob/main/latency.png" alt="latency" width="600" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
 
 
 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.