Update README.md

README.md

@@ -28,12 +28,18 @@ Hindi-Gemma-2B-instruct is an instruction-tuned Hindi large language model (LLM)
 # TO do inference using the LORA adapters
 
 from unsloth import FastLanguageModel
+
 model, tokenizer = FastLanguageModel.from_pretrained(
+    
     model_name = "Ellight/gemma-2b-bnb-4bit", # 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
 
 prompt = """
@@ -53,4 +59,5 @@ inputs = tokenizer(
 ], return_tensors = "pt").to("cuda")
 
 outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)
+
 tokenizer.batch_decode(outputs)