Upload README.md with huggingface_hub

README.md

@@ -1,5 +1,39 @@
----
-license: other
-license_name: mrl
-license_link: LICENSE
----
+---
+license: other
+license_name: mrl
+language:
+- en
+tags:
+- chat
+- mlx
+- mlx-my-repo
+pipeline_tag: text-generation
+library_name: transformers
+base_model: MarsupialAI/Monstral-123B-v2
+---
+
+# ainugget/Monstral-123B-v2-Q2-mlx
+
+The Model [ainugget/Monstral-123B-v2-Q2-mlx](https://huggingface.co/ainugget/Monstral-123B-v2-Q2-mlx) was converted to MLX format from [MarsupialAI/Monstral-123B-v2](https://huggingface.co/MarsupialAI/Monstral-123B-v2) 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("ainugget/Monstral-123B-v2-Q2-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)
+```