Update README.md

README.md

@@ -39,6 +39,19 @@ pip install bitsandbytes
 
 ```python
 
+# Activate 4-bit precision base model loading (bool)
+load_in_4bit = True
+
+# Activate nested quantization for 4-bit base models (double quantization) (bool)
+bnb_4bit_use_double_quant = True
+
+# Quantization type (fp4 or nf4) (string)
+bnb_4bit_quant_type = "nf4"
+
+# Compute data type for 4-bit base models
+bnb_4bit_compute_dtype = torch.bfloat16
+
+
 def load_model_tokenizer(model_name: str, bnb_config: BitsAndBytesConfig) -> Tuple[AutoModelForCausalLM, AutoTokenizer]:
     """
     Load the model and tokenizer from the HuggingFace model hub using quantization.