Update usage on Mac and GPUs do not support BF16

README.md

@@ -112,23 +112,31 @@ Currently MiniCPM-V (i.e., OmniLMM-3B) can be deployed on mobile phones with And
 
 
 ## Usage
-Requirements:  tested on python 3.10 
+Inference using Huggingface transformers on Nivdia GPUs or Mac with MPS (Apple silicon or AMD GPUs). Requirements tested on python 3.10：
 ```
 Pillow==10.1.0
 timm==0.9.10
-torch==2.0.1
-torchvision==0.15.2
+torch==2.1.2
+torchvision==0.16.2
 transformers==4.36.0
 sentencepiece==0.1.99
 ```
 
 ```python
+# test.py
 import torch
 from PIL import Image
 from transformers import AutoModel, AutoTokenizer
 
-model = AutoModel.from_pretrained('openbmb/MiniCPM-V', trust_remote_code=True)
-model = model.to(dtype=torch.bfloat16)
+model = AutoModel.from_pretrained('openbmb/MiniCPM-V', trust_remote_code=True, torch_dtype=torch.bfloat16)
+# For Nvidia GPUs support BF16 (like A100, H100, RTX3090)
+model = model.to(device='cuda', dtype=torch.bfloat16)
+# For Nvidia GPUs do NOT support BF16 (like V100, T4, RTX2080)
+#model = model.to(device='cuda', dtype=torch.float16)
+# For Mac with MPS (Apple silicon or AMD GPUs).
+# Run with `PYTORCH_ENABLE_MPS_FALLBACK=1 python test.py`
+#model = model.to(device='mps', dtype=torch.float16)
+
 tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V', trust_remote_code=True)
 model.eval().cuda()
 
@@ -158,5 +166,5 @@ Please look at [GitHub](https://github.com/OpenBMB/OmniLMM) for more detail abou
 * Please contact [email protected] to obtain a written authorization for commercial uses. Free commercial use is also allowed after registration.
 
 #### Statement
-* As an LLM, MiniCPM-V generates contents by learning a large mount of texts, but it cannot comprehend, express personal opinions or make value judgement. Anything generated by MiniCPM-V does not represent the views and positions of the model developers
+* As a LLM, MiniCPM-V generates contents by learning a large mount of texts, but it cannot comprehend, express personal opinions or make value judgement. Anything generated by MiniCPM-V does not represent the views and positions of the model developers
 * We will not be liable for any problems arising from the use of the MinCPM-V open Source model, including but not limited to data security issues, risk of public opinion, or any risks and problems arising from the misdirection, misuse, dissemination or misuse of the model.