Update README.md

README.md

@@ -79,17 +79,14 @@ for i in range(len(output)):
     print('\033[92m' + tokenizer.decode(output[i], skip_special_tokens=True) + '\033[0m\n')
 ```
 
-Example of generated prompts:
+No comma style:
 ![constrastive search](./constrastive_search.png)
 
+<br>
 
-## Greedy Search
-
-Replace `output` with
-
+To bring back the commas, assign output without penalty_alpha:
 ```python
-output = model.generate(input_ids, do_sample=True, temperature=temperature, top_k=top_k, max_length=max_length, num_return_sequences=num_return_sequences, early_stopping=True)
+output = model.generate(input_ids, do_sample=True, temperature=temperature, top_k=top_k, max_length=max_length, num_return_sequences=num_return_sequences, repetition_penalty=repitition_penalty, no_repeat_ngram_size=1, early_stopping=True)
 ```
 
-Example of generated prompts:
-![greedy search](./greedy_search.png)
+![constrastive search](./contrastive_comma_style.png)