Update README.md

README.md

@@ -3,7 +3,31 @@ license: apache-2.0
 base_model: stepfun-ai/Step-3.5-Flash
 tags:
 - mlx
+pipeline_tag: text-generation
 ---
 
-# e1732a364fed/Step-3.5-Flash-mlx-8Bit
-The Model [e1732a364fed/Step-3.5-Flash-mlx-8Bit](https://huggingface.co/e1732a364fed/Step-3.5-Flash-mlx-8Bit) was converted to MLX format...
+# mlx-community/Step-3.5-Flash-8bit
+
+The Model [mlx-community/Step-3.5-Flash-8bit](https://huggingface.co/mlx-community/Step-3.5-Flash-8bit) was converted to MLX format from [stepfun-ai/Step-3.5-Flash](https://huggingface.co/stepfun-ai/Step-3.5-Flash) using mlx-lm version **0.30.6**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Step-3.5-Flash-8bit")
+
+prompt="hello"
+
+if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```