Update README.md

README.md

@@ -119,21 +119,22 @@ model, tokenizer = load_model(
 ```
 Inference:
 ```python
-def generate_response (model,tokenizer,text_input="What is the best biomaterial for superior strength?",
-                      num_return_sequences=1,
-                      temperature=1., #the higher the temperature, the more creative the model becomes
-                      max_new_tokens=127,
-                      num_beams=1,
+def generate_response (model, tokenizer,
+                      text_input="What is the best biomaterial for superior strength?",
+                      num_return_sequences = 1,
+                      temperature = 0.75,  
+                      max_new_tokens = 127,
+                      num_beams = 1,
                       top_k = 50,
-                      top_p =0.9,repetition_penalty=1.,eos_token_id=2,verbatim=False,
-                      exponential_decay_length_penalty_fac=None,add_special_tokens=True,  
+                      top_p = 0.9, repetition_penalty=1., eos_token_id=2, verbatim=False,
+                      add_special_tokens=True,  
                       ):
     inputs = tokenizer(text_input,  
     with torch.no_grad():
           outputs = model.generate(input_ids = inputs["input_ids"],
-                                    attention_mask = inputs["attention_mask"] , # This is usually done automatically by the tokenizer
+                                    attention_mask = inputs["attention_mask"] ,  
                                     max_new_tokens=max_new_tokens,
-                                    temperature=temperature, #value used to modulate the next token probabilities.
+                                    temperature=temperature, 
                                     num_beams=num_beams,
                                     top_k = top_k,
                                     top_p = top_p,