Update README.md

add important download info

README.md

@@ -11,7 +11,23 @@ This is `bge-m3-onnx-o4` weights of the original [`BAAI/bge-m3`](https://hugging
 - [x] Multi-Linguality: It can support more than **100** working languages.
 - [x] Multi-Granularity: It is able to process inputs of different granularities, spanning from short sentences to long documents of up to **8192** tokens.
 
-## Usage
+## Usage 
+
+### IMPORTANT - DOWNLOAD MODEL WEIGHTS
+
+Please see the instructions below.
+
+1. **Download** the checkpoint: For some reason you cannot directly load from this online version (you will get an exception).
+Please download this repo as below:
+
+```
+# pip install huggingface-hub
+ 
+from huggingface_hub import snapshot_download
+
+snapshot_download(repo_id="hooman650/bge-m3-onnx-o4",local_dir="bge-m3-onnx")
+```
+
 
 ### Dense Retrieval
 
@@ -26,7 +42,8 @@ from optimum.onnxruntime import ORTModelForFeatureExtraction
 from transformers import AutoTokenizer
 import torch
 
-model = ORTModelForFeatureExtraction.from_pretrained("hooman650/bge-m3-onnx-o4", provider="CUDAExecutionProvider")
+# Make sure that you download the model weights locally to `bge-m3-onnx`
+model = ORTModelForFeatureExtraction.from_pretrained("bge-m3-onnx", provider="CUDAExecutionProvider") # omit provider for CPU usage.
 tokenizer = AutoTokenizer.from_pretrained("hooman650/bge-m3-onnx-o4")
 
 sentences = [