readme: usage and performance

README.md

@@ -160,6 +160,47 @@ The data and training details are described in the technical report (coming soon
 
 ## Usage
 
+**<details><summary>Apply mean pooling when integrating the model.</summary>**
+<p>
+
+### Why Use Mean Pooling?
+
+Mean pooling takes all token embeddings from the model's output and averages them at the sentence or paragraph level. 
+This approach has been shown to produce high-quality sentence embeddings.
+
+We provide an `encode` function that handles this for you automatically.
+
+However, if you're working with the model directly, outside of the `encode` function, 
+you'll need to apply mean pooling manually. Here's how you can do it:
+
+
+```python
+import torch
+import torch.nn.functional as F
+from transformers import AutoTokenizer, AutoModel
+
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0]
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+sentences = ['How is the weather today?', 'What is the current weather like today?']
+
+tokenizer = AutoTokenizer.from_pretrained('jinaai/jina-embeddings-v3')
+model = AutoModel.from_pretrained('jinaai/jina-embeddings-v3', trust_remote_code=True)
+
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+embeddings = F.normalize(embeddings, p=2, dim=1)
+```
+
+</p>
+</details>
+
 1. The easiest way to starting using jina-clip-v1-en is to use Jina AI's [Embeddings API](https://jina.ai/embeddings/).
 2. Alternatively, you can use Jina CLIP directly via transformers package.