add README.md

README.md

@@ -1,3 +1,30 @@
----
-license: apache-2.0
----
+# Qwen3-32B GPTQ 4bit
+
+[GPTQModel](https://github.com/ModelCloud/GPTQModel)
+
+
+```python3
+from datasets import load_dataset
+from gptqmodel import GPTQModel, QuantizeConfig
+
+import sys
+
+model_id = sys.argv[1]
+print(model_id)
+quant_path = "quantized_model"
+
+calibration_dataset = load_dataset(
+    "allenai/c4",
+    data_files="en/c4-train.00001-of-01024.json.gz",
+    split="train"
+  ).select(range(1024))["text"]
+
+quant_config = QuantizeConfig(bits=4, group_size=128)
+
+model = GPTQModel.load(model_id, quant_config)
+
+# increase `batch_size` to match gpu/vram specs to speed up quantization
+model.quantize(calibration_dataset, batch_size=2)
+
+model.save(quant_path)
+```