Update README.md

README.md

@@ -86,6 +86,7 @@ The fastest way to get started with BLING is through direct import in transforme
     tokenizer = AutoTokenizer.from_pretrained("llmware/bling-1b-0.1")  
     model = AutoModelForCausalLM.from_pretrained("llmware/bling-1b-0.1")  
 
+Please refer to the two tester .py files in the Files repository, which includes 200 samples and script to test the model.  
 
 The BLING model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
 
@@ -122,7 +123,6 @@ If you are using a HuggingFace generation script:
 
     output_only = tokenizer.decode(outputs[0][start_of_output:],skip_special_tokens=True)
 
-Please also refer to two sample test scripts in the files repository for full examples.  
 
 ## Citation [optional]