Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,64 @@
+---
+language:
+- en
+- fr
+- de
+- es
+- pt
+- it
+- ja
+- ko
+- ru
+- zh
+- ar
+- fa
+- id
+- ms
+- ne
+- pl
+- ro
+- sr
+- sv
+- tr
+- uk
+- vi
+- hi
+- bn
+license: apache-2.0
+library_name: mlx
+inference: false
+base_model: mlx-community/Magistral-Small-2506-bf16
+extra_gated_description: If you want to learn more about how we process your personal
+  data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
+pipeline_tag: text-generation
+tags:
+- mlx
+- mlx
+- mlx-my-repo
+---
+
+# janboe91/Magistral-Small-2506-bf16-mlx-6Bit
+
+The Model [janboe91/Magistral-Small-2506-bf16-mlx-6Bit](https://huggingface.co/janboe91/Magistral-Small-2506-bf16-mlx-6Bit) was converted to MLX format from [mlx-community/Magistral-Small-2506-bf16](https://huggingface.co/mlx-community/Magistral-Small-2506-bf16) using mlx-lm version **0.22.3**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("janboe91/Magistral-Small-2506-bf16-mlx-6Bit")
+
+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)
+```