Update README.md

README.md

@@ -13,6 +13,43 @@ A CLIP ViT-L/14 model trained using [OpenCLIP](https://github.com/mlfoundations/
 
 # How to Use
 
+## Installation
+
+```bash
+$ pip install open_clip_torch
+```
+
+## Zero-shot Image Classification
+```python
+import open_clip
+
+model, preprocess = open_clip.create_model_from_pretrained('hf-hub:speed/llm-jp-roberta-ViT-L-14-relaion-1.5B-lr5e-4-bs8k-accum4-20241218-epoch90')
+tokenizer = open_clip.get_tokenizer('hf-hub:speed/llm-jp-roberta-ViT-L-14-relaion-1.5B-lr5e-4-bs8k-accum4-20241218-epoch90')
+
+import torch
+from PIL import Image
+import requests
+
+url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
+image = Image.open(requests.get(url, stream=True).raw)
+image = preprocess(image).unsqueeze(0)
+text = tokenizer(["猫", "犬", "鳥"])
+
+with torch.no_grad(), torch.cuda.amp.autocast():
+    image_features = model.encode_image(image)
+    text_features = model.encode_text(text)
+    image_features /= image_features.norm(dim=-1, keepdim=True)
+    text_features /= text_features.norm(dim=-1, keepdim=True)
+
+    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)
+
+print("Label probs:", text_probs)
+```
+
+Reference: 
+- [Using OpenCLIP at Hugging Face](https://huggingface.co/docs/hub/en/open_clip), HuggingFace Docs
+- OpenCLIP [repository](https://github.com/mlfoundations/open_clip)
+
 
 # Training Details