Add model card with tags

README.md

@@ -0,0 +1,69 @@
+---
+base_model: Qwen/Qwen3-Reranker-8B
+library_name: mlx-embeddings
+tags:
+  - mlx
+  - reranker
+  - text-classification
+  - qwen3
+  - apple-silicon
+  - fp16
+  - cross-encoder
+language:
+  - multilingual
+license: apache-2.0
+pipeline_tag: text-classification
+datasets:
+  - Qwen/Reranker-Multilingual-General-Instruct
+---
+
+# Qwen3-Reranker-8B — MLX fp16
+
+[Qwen/Qwen3-Reranker-8B](https://huggingface.co/Qwen/Qwen3-Reranker-8B) converted to MLX format in **float16** precision for Apple Silicon.
+
+## Model Details
+
+| Property | Value |
+|---|---|
+| Base model | [Qwen/Qwen3-Reranker-8B](https://huggingface.co/Qwen/Qwen3-Reranker-8B) |
+| Parameters | 8B |
+| Architecture | Qwen3 (decoder-based, cross-encoder) |
+| Precision | float16 |
+| Max context length | 32,768 tokens |
+| Languages | 100+ |
+| Scoring | "yes"/"no" logit comparison |
+| Converted with | [mlx-embeddings](https://github.com/Blaizzy/mlx-embeddings) v0.1.0 |
+
+## Usage
+
+```bash
+pip install mlx-embeddings
+```
+
+```python
+from mlx_embeddings import load
+import mlx.core as mx
+
+model, tokenizer = load("bsisduck/Qwen3-Reranker-8B-fp16-mlx")
+
+scores = model.process({
+    "instruction": "Given a web search query, retrieve relevant passages that answer the query",
+    "query": {"text": "What is MLX?"},
+    "documents": [
+        {"text": "MLX is Apple's array framework for machine learning on Apple Silicon."},
+        {"text": "Python is a programming language."},
+    ],
+}, processor=tokenizer)
+
+# Higher score = more relevant
+print(scores)
+```
+
+## Hardware Requirements
+
+- Apple Silicon Mac (M1/M2/M3/M4)
+- ~16 GB unified memory
+
+## Original Model
+
+See [Qwen/Qwen3-Reranker-8B](https://huggingface.co/Qwen/Qwen3-Reranker-8B) for benchmarks, training details, and full documentation.