Update README.md

README.md

@@ -40,8 +40,9 @@ Testing is a work in progress, we decide to share both model variations with com
 - [Medical chat Dialogs](https://github.com/project-baize/baize)
 
 - ### About pre-processing
-
+Ask2Democracy-cfqa-salud-pension dataset was pre-processed in a conversational style like this:
 ```python
+
 def format_instruction_without_context(example):
   example["topic"] = example['input']
   input = "La conversación entre un humano y un asistente de IA."
@@ -54,6 +55,22 @@ def format_instruction_without_context(example):
     example["topic"] += f" ({topics})"
   example["input"] = input
   return example`
+
+def format_instruction_with_context(example):
+  example["topic"] = example['input']
+  context = example['instruction'].replace("Given the context please answer the question. Context:","")
+  context = ' '.join(context.strip().split())[1:-3]
+  input = "La conversación entre un humano y un asistente de IA."
+  input += "\n[|Human|] "+example['input']+f"\nPara responder la pregunta, usa el siguiente contexto:\n{context}"
+  input += "\n[|AI|] "+example["output"]
+  if len(example["topics"])>0:
+    topics = ", ".join(example["topics"])
+    input += "\n[|Human|] "+"¿En cuáles tópicos clasificarías su respuesta?"
+    input += "\n[|AI|] "+f"Aquí una lista de tópicos: {topics}."
+    example["topic"] += f" ({topics})"
+  example["input"] = input
+  return example
+
 ```