Update README.md

README.md

@@ -59,6 +59,19 @@ BLIP2 has not been tested in real world applications. It should not be directly
 
 For code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/blip-2#transformers.Blip2ForConditionalGeneration.forward.example).
 
+### Memory requirements
+
+The memory requirements differ based on the precision one uses. One can use 4-bit inference using [Bitsandbytes](https://huggingface.co/blog/4bit-transformers-bitsandbytes), which greatly reduce the memory requirements.
+
+Training requires 4 times the 
+
+| dtype             | Largest Layer or Residual Group | Total Size | Training using Adam |
+|-------------------|---------------------------------|------------|----------------------|
+| float32           | 490.94 MB                       | 14.43 GB   | 57.72 GB             |
+| float16/bfloat16  | 245.47 MB                       | 7.21 GB    | 28.86 GB             |
+| int8              | 122.73 MB                       | 3.61 GB    | 14.43 GB             |
+| int4              | 61.37 MB                        | 1.8 GB     | 7.21 GB              |
+
 #### Running the model on CPU
 
 <details>