Update README.md

README.md

@@ -18,6 +18,34 @@ finetuinng with
 
 
 # code
+
+''python
+from unsloth import FastLanguageModel
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "EpistemeAI/EpistemeAI-codegemma-2-9b", # YOUR MODEL YOU USED FOR TRAINING
+    max_seq_length = max_seq_length,
+    dtype = dtype,
+    load_in_4bit = load_in_4bit,
+)
+FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+
+# alpaca_prompt = You MUST copy from above!
+
+inputs = tokenizer(
+[
+    alpaca_prompt.format(
+        "Create a function to calculate the sum of a sequence of integers.", # instruction
+        "", # input
+        "", # output - leave this blank for generation!
+    )
+], return_tensors = "pt").to("cuda")
+
+outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)
+tokenizer.batch_decode(outputs)
+
+''
+
 Formated text
 ''python
  formatted_text = f"""Below is an instruction that describes a task. \