Update README.md

README.md

@@ -5,4 +5,16 @@ language:
 base_model:
 - deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
 ---
-AWQ 4 bits quantization from DeepSeek-R1-Distill-Qwen-32B commit 10d6a0388c80991c8fd8b54223146e7cbe33dfa5
+AWQ 4 bits quantization from DeepSeek-R1-Distill-Qwen-32B commit 10d6a0388c80991c8fd8b54223146e7cbe33dfa5
+
+```python
+from awq import AutoAWQForCausalLM
+from transformers import AutoTokenizer
+model_name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
+commit_hash = "10d6a0388c80991c8fd8b54223146e7cbe33dfa5"
+# Download the model and tokenizer at the specific commit hash
+model = AutoAWQForCausalLM.from_pretrained(model_name, revision=commit_hash)
+tokenizer = AutoTokenizer.from_pretrained(model_name, revision=commit_hash)
+quant_config = { "zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM" }
+model.quantize(tokenizer, quant_config=quant_config)
+```