remove gpu type for memory usage

README.md

@@ -45,20 +45,18 @@ The model was trained and tested in the following languages:
 
 ## GPU Memory usage
 
-| GPU Info                                  | Quantization type |   Memory   |
-|:------------------------------------------|-------------------|-----------:|
-| NVIDIA A10                                | FP16              |    578 MiB |
-| NVIDIA A10                                | FP32              |   1062 MiB |
-| NVIDIA T4                                 | FP16              |    547 MiB |
-| NVIDIA T4                                 | FP32              |   1060 MiB |
-
-Note that GPU memory usage only includes how much GPU memory the actual model consumes those specific GPUs with a batch
+| Quantization type                                |   Memory   |
+|:-------------------------------------------------|-----------:|
+| FP16                                             |    547 MiB |
+| FP32                                             |   1060 MiB |
+
+Note that GPU memory usage only includes how much GPU memory the actual model consumes on an NVIDIA T4 GPU with a batch
 size of 32. It does not include the fix amount of memory that is consumed by the ONNX Runtime upon initialization which
 can be around 0.5 to 1 GiB depending on the used GPU.
 
 ## Requirements
 
-- Minimal Sinequa version: 11.10.0
+- Minimal Sinequa version: 11.10.0 (for NVIDIA L4 with FP16: 11.11.0)
 - [Cuda compute capability](https://developer.nvidia.com/cuda-gpus): above 5.0 (above 6.0 for FP16 use)
 
 ## Model Details