Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,37 @@
+---
+license: apache-2.0
+datasets:
+- qingy2024/FineQwQ-142k
+language:
+- en
+base_model: qingy2024/UwU-7B-Instruct
+pipeline_tag: text-generation
+tags:
+- mlx
+---
+
+# prdnr/UwU-7B-Instruct-Q4-mlx
+
+The Model [prdnr/UwU-7B-Instruct-Q4-mlx](https://huggingface.co/prdnr/UwU-7B-Instruct-Q4-mlx) was converted to MLX format from [qingy2024/UwU-7B-Instruct](https://huggingface.co/qingy2024/UwU-7B-Instruct) using mlx-lm version **0.20.5**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("prdnr/UwU-7B-Instruct-Q4-mlx")
+
+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)
+```