Update README.md

README.md

@@ -85,6 +85,19 @@ Usage:
     text = tokenizer.batch_decode(outputs,skip_special_tokens=True)[0]
     print(text)
     
+Usage (with quantization):
+
+    bnb_config = BitsAndBytesConfig(load_in_4bit=True,
+                                    bnb_4bit_quant_type='nf4',
+                                    bnb_4bit_compute_dtype=torch.bfloat16,
+                                    bnb_4bit_use_double_quant=True)
+    [...]
+
+    model = AutoModelForCausalLM.from_pretrained(..., quantization_config=bnb_config)
+
+    [...]
+    
+    fine_tuned_model = PeftModel.from_pretrained(... , quantization_config=bnb_config)
 
 
 Example: