Add readme

README.md

@@ -1,3 +1,53 @@
 ---
 license: apache-2.0
 ---
+
+# Magistral-Small-2506-FP8-dynamic
+
+Quantized version of [Magistral-Small-2506](https://huggingface.co/mistralai/Magistral-Small-2506).
+
+## Creation
+
+This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet
+below.
+
+```python
+import argparse
+import os
+
+from llmcompressor.modifiers.quantization import QuantizationModifier
+from llmcompressor.transformers import oneshot
+from transformers import AutoModelForCausalLM
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Quantize a transformer model to FP8')
+    parser.add_argument('--model_id', type=str, required=True,
+                        help='The model ID from HuggingFace (e.g., "meta-llama/Meta-Llama-3-8B-Instruct")')
+    parser.add_argument('--save_path', type=str, default='.',
+                        help='Custom path to save the quantized model. If not provided, will use model_name-FP8-dynamic')
+    args = parser.parse_args()
+
+    # Load model
+    model = AutoModelForCausalLM.from_pretrained(
+        args.model_id, device_map="auto", torch_dtype="auto", trust_remote_code=True,
+    )
+
+    # Configure the quantization algorithm and scheme
+    recipe = QuantizationModifier(
+        targets="Linear", scheme="FP8_DYNAMIC", ignore=["lm_head"]
+    )
+
+    # Apply quantization
+    oneshot(model=model, recipe=recipe)
+
+    save_path = os.path.join(args.save_path, args.model_id.split("/")[1] + "-FP8-dynamic")
+    os.makedirs(save_path, exist_ok=True)
+
+    # Save to disk in compressed-tensors format
+    model.save_pretrained(save_path)
+    print(f"Model and tokenizer saved to: {save_path}")
+
+if __name__ == "__main__":
+    main()
+```