Upload folder using huggingface_hub

README.md

@@ -21094,25 +21094,32 @@ model-index:
       value: 78.51132446157838
 ---
 
-# mlx-community/modernbert-embed-base-8bit
+        # mlx-community/modernbert-embed-base-8bit
 
-The Model [mlx-community/modernbert-embed-base-8bit](https://huggingface.co/mlx-community/modernbert-embed-base-8bit) was converted to MLX format from [nomic-ai/modernbert-embed-base](https://huggingface.co/nomic-ai/modernbert-embed-base) using mlx-lm version **0.0.3**.
+        The Model [mlx-community/modernbert-embed-base-8bit](https://huggingface.co/mlx-community/modernbert-embed-base-8bit) was converted to MLX format from [nomic-ai/modernbert-embed-base](https://huggingface.co/nomic-ai/modernbert-embed-base) using mlx-lm version **0.0.3**.
 
-## Use with mlx
+        ## Use with mlx
 
-```bash
-pip install mlx-embeddings
-```
+        ```bash
+        pip install mlx-embeddings
+        ```
 
-```python
-from mlx_embeddings import load, generate
+        ```python
+        from mlx_embeddings import load, generate
+        import mlx.core as mx
 
-model, tokenizer = load("mlx-community/modernbert-embed-base-8bit")
+        model, tokenizer = load("mlx-community/modernbert-embed-base-8bit")
 
-# For text embeddings
-output = generate(model, processor, None, texts=["I like grapes", "I like fruits"])
-# Get text embeddings from the output
-embeddings = output.text_embeds  # Shape: [batch_size, hidden_size]
+        # For text embeddings
+        output = generate(model, processor, texts=["I like grapes", "I like fruits"])
+        embeddings = output.text_embeds  # Normalized embeddings
 
+        # Compute dot product between normalized embeddings
+        similarity_matrix = mx.matmul(embeddings, embeddings.T)
 
-```
+        print("
+Similarity matrix between texts:")
+        print(similarity_matrix)
+
+
+        ```