Update README.md

README.md

@@ -38,6 +38,33 @@ response = pipe(conv, max_new_tokens=2048)[0]['generated_text'][-1]['content']
 print(response)
 ```
 
+To use the model with quantization:
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+import torch
+
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16
+)
+
+model_id = "nroggendorff/mayo"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config)
+
+prompt = "<|user|>What color is the sky?</s>"
+inputs = tokenizer(prompt, return_tensors="pt")
+
+outputs = model.generate(**inputs, max_new_tokens=10)
+
+generated_text = tokenizer.batch_decode(outputs)[0]
+print(generated_text)
+```
+
 ## License
 
 This project is licensed under the MIT License.