Update README.md

README.md

@@ -32,6 +32,19 @@ This model is a function calling version of [google/gemma-2-2b](https://huggingf
 ```python
 from unsloth import FastLanguageModel
 
+max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
+dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
+load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "gemma2-2b-xlam-function-calling", # YOUR MODEL YOU USED FOR TRAINING
+    max_seq_length = 1024,
+    dtype = dtype,
+    load_in_4bit = load_in_4bit,
+)
+FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+
+
 alpaca_prompt = """Below are the tools that you have access to these tools. Use them if required.
 
 ### Tools: