Update README.md

README.md

@@ -198,7 +198,25 @@ en español responde solo en json:
 <start_of_turn>model
 """
 
+inputs = tokenizer.encode(txt,
+                          return_tensors="pt",
+                          add_special_tokens=False).to("cuda:0")
+max_new_tokens=1500
+generation_config = GenerationConfig(
+              max_new_tokens=max_new_tokens,
+              temperature=0.15,
+              # top_p=0.55,
+              top_k=50,
+              repetition_penalty=1.1,
+              do_sample=True,
+          )
+outputs = base_model.generate(generation_config=generation_config,
+                         input_ids=inputs,
+                         stopping_criteria=stopping_criteria_list,)
+print(tokenizer.decode(outputs[0], skip_special_tokens=False) )
+```
 
+```
 '''
 ### OUTPUT EXAMPLE
 <start_of_turn>model
@@ -228,23 +246,4 @@ en español responde solo en json:
   ]
 }<end_of_turn>
 '''
-
-
-
-inputs = tokenizer.encode(txt,
-                          return_tensors="pt",
-                          add_special_tokens=False).to("cuda:0")
-max_new_tokens=1500
-generation_config = GenerationConfig(
-              max_new_tokens=max_new_tokens,
-              temperature=0.15,
-              # top_p=0.55,
-              top_k=50,
-              repetition_penalty=1.1,
-              do_sample=True,
-          )
-outputs = base_model.generate(generation_config=generation_config,
-                         input_ids=inputs,
-                         stopping_criteria=stopping_criteria_list,)
-print(tokenizer.decode(outputs[0], skip_special_tokens=False) )
-```
+```