Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,44 @@
+---
+license: other
+license_name: nvidia-open-model-license
+license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
+inference: false
+fine-tuning: false
+language:
+- en
+tags:
+- nvidia
+- llama3.3
+- mlx
+- mlx-my-repo
+datasets:
+- nvidia/HelpSteer3
+base_model: nvidia/Llama-3.3-Nemotron-70B-Reward-Principle
+library_name: transformers
+---
+
+# McG-221/Llama-3.3-Nemotron-70B-Reward-Principle-mlx-5Bit
+
+The Model [McG-221/Llama-3.3-Nemotron-70B-Reward-Principle-mlx-5Bit](https://huggingface.co/McG-221/Llama-3.3-Nemotron-70B-Reward-Principle-mlx-5Bit) was converted to MLX format from [nvidia/Llama-3.3-Nemotron-70B-Reward-Principle](https://huggingface.co/nvidia/Llama-3.3-Nemotron-70B-Reward-Principle) using mlx-lm version **0.28.3**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("McG-221/Llama-3.3-Nemotron-70B-Reward-Principle-mlx-5Bit")
+
+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)
+```