Update README.md

README.md

@@ -36,18 +36,20 @@ model, tokenizer = FastLanguageModel.from_pretrained(
 )
 FastLanguageModel.for_inference(model) # Enable native 2x faster inference
 
-alpaca_prompt = """
+prompt = """
 ### Instruction:
 {}
 
 ### Response:
 {}"""
+
 inputs = tokenizer(
 [
-    alpaca_prompt.format(
+    prompt.format(
         "शतरंज बोर्ड पर कितने वर्ग होते हैं?", # instruction
         "", # output - leave this blank for generation!
     )
+
 ], return_tensors = "pt").to("cuda")
 
 outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)