Process conversation datasets;

Dataset.py

@@ -6,11 +6,15 @@ from datasets import load_dataset, concatenate_datasets
 class Dataset:
     def scan(self, location: str, tokenizer, context: Context):
         print(f"Scanning dataset directory {location}")
-        
+
-        directory = pathlib.Path(location)
+        customChatTemplate = None
-        files = [f for f in directory.iterdir() if f.is_file()]
+        if context.locCustomPromptTemplate != None:
+            with open(context.locCustomPromptTemplate, 'r') as file:
+                customChatTemplate = file.read()
         
         datasets = []
+        directory = pathlib.Path(location)
+        files = [f for f in directory.iterdir() if f.is_file()]
         for file in files:
             print(file.name)
             
@@ -23,9 +27,11 @@ class Dataset:
                 if "text" in qaDataset['train'].features:
                     self.__loadTextDataset(qaDataset, datasets, tokenizer)
                 elif "history" in qaDataset['train'].features or "instruct" in qaDataset['train'].features or "completion" in qaDataset['train'].features or "question" in qaDataset['train'].features or "answer" in qaDataset['train'].features:
-                    self.__loadQaDataset(qaDataset, datasets, tokenizer, context)
+                    self.__loadQaDataset(qaDataset, datasets, tokenizer, customChatTemplate, context)
+                elif "conversation" in qaDataset['train'].features:
+                    self.__loadConversationDataset(qaDataset, datasets, tokenizer, customChatTemplate, context)
                 else:
-                    print("Cannot load dataset, json dataset neither contains 'text' nor 'question', 'answer'")
+                    print("Cannot load dataset, json dataset is malformed")
         
         if len(datasets) == 0:
             raise Exception("No datasets have been found. Check configuration")
@@ -50,13 +56,8 @@ class Dataset:
         def datasetTextEncoder(record):
             return tokenizer(record["text"])
         datasets.append(textDataset.map(datasetTextEncoder)["train"])
-
+    
-    def __loadQaDataset(self, qaDataset, datasets, tokenizer, context):
+    def __loadQaDataset(self, qaDataset, datasets, tokenizer, customChatTemplate, context):
-        customChatTemplate = None
-        if context.locCustomPromptTemplate != None:
-            with open(context.locCustomPromptTemplate, 'r') as file:
-                customChatTemplate = file.read()
-        
         def datasetChatEncoder(record):
             chat = []
             try:
@@ -85,8 +86,37 @@ class Dataset:
             except KeyError:
                 pass
             
-            if context.showChatTemplate:
+            return self.__format(chat, tokenizer, customChatTemplate, context)
-                print(tokenizer.apply_chat_template(chat, chat_template = customChatTemplate, add_generation_prompt = False, tokenize = False, return_dict = False))
+        
-            
-            return tokenizer.apply_chat_template(chat, chat_template = customChatTemplate, add_generation_prompt = False, tokenize = True, return_dict = True)
         datasets.append(qaDataset.map(datasetChatEncoder, remove_columns=qaDataset.column_names["train"])["train"])
+    
+    def __loadConversationDataset(self, qaDataset, datasets, tokenizer, customChatTemplate, context):
+        def datasetConversationEncoder(batch):
+            inputIds = []
+            attentionMask = []
+            for records in batch['conversation']:
+                chat = []
+                cnt = 0
+                for record in records:
+                    curCnt = len(tokenizer.tokenize(record['user'])) + len(tokenizer.tokenize(record['assistant'])) + 15
+                    if cnt + curCnt >= context.trMaxSeqLength:
+                        encoded = self.__format(chat, tokenizer, customChatTemplate, context)
+                        inputIds.append(encoded['input_ids'])
+                        attentionMask.append(encoded['attention_mask'])
+                        chat = []
+                        cnt = curCnt
+                    else:
+                        cnt += curCnt
+                    chat.append({"role": "user", "content": f"{record['user']}"})
+                    chat.append({"role": "assistant", "content": f"{record['assistant']}"})
+                encoded = self.__format(chat, tokenizer, customChatTemplate, context)
+                inputIds.append(encoded['input_ids'])
+                attentionMask.append(encoded['attention_mask'])
+            return {"input_ids": inputIds, "attention_mask": attentionMask}
+        
+        datasets.append(qaDataset.map(datasetConversationEncoder, batched = True, remove_columns=qaDataset.column_names["train"])["train"])
+    
+    def __format(self, chat, tokenizer, customChatTemplate, context):
+        if context.showChatTemplate:
+            print(tokenizer.apply_chat_template(chat, chat_template = customChatTemplate, add_generation_prompt = False, tokenize = False, return_dict = False))
+        return tokenizer.apply_chat_template(chat, chat_template = customChatTemplate, add_generation_prompt = False, tokenize = True, return_dict = True)