Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,36 @@
+---
+license: other
+base_model: facebook/KernelLLM
+datasets:
+- ScalingIntelligence/KernelBench
+- GPUMODE/KernelBook
+library_name: transformers
+tags:
+- mlx
+---
+
+# Felladrin/KernelLLM-mlx-6Bit
+
+The Model [Felladrin/KernelLLM-mlx-6Bit](https://huggingface.co/Felladrin/KernelLLM-mlx-6Bit) was converted to MLX format from [facebook/KernelLLM](https://huggingface.co/facebook/KernelLLM) 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("Felladrin/KernelLLM-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)
+```