Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,46 @@
+---
+license: mit
+license_link: https://huggingface.co/microsoft/phi-4/resolve/main/LICENSE
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- phi
+- phi4
+- unsloth
+- nlp
+- math
+- code
+- chat
+- conversational
+- mlx
+- mlx-my-repo
+base_model: unsloth/phi-4
+library_name: transformers
+---
+
+# sigjhl/phi-4-mlx-8Bit
+
+The Model [sigjhl/phi-4-mlx-8Bit](https://huggingface.co/sigjhl/phi-4-mlx-8Bit) was converted to MLX format from [unsloth/phi-4](https://huggingface.co/unsloth/phi-4) using mlx-lm version **0.21.5**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("sigjhl/phi-4-mlx-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)
+```