From 6abb7f6a1603f4955f0e3851f7bbcd4026f76ad7 Mon Sep 17 00:00:00 2001
From: NanoCode012 <kevinvong@rocketmail.com>
Date: Mon, 29 May 2023 13:54:06 +0900
Subject: [PATCH] Lint datasets

---
 src/axolotl/datasets.py | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/src/axolotl/datasets.py b/src/axolotl/datasets.py
index c7bb9fbfe..1e72be114 100644
--- a/src/axolotl/datasets.py
+++ b/src/axolotl/datasets.py
@@ -1,3 +1,5 @@
+"""Module containing Dataset functionality"""
+
 import logging
 from typing import List
 
@@ -14,7 +16,14 @@ from .prompt_tokenizers import PromptTokenizingStrategy, InvalidDataException
 
 
 class TokenizedPromptDataset(IterableDataset):
-    def __init__(
+    """
+    Iterable dataset that returns tokenized prompts from a stream of text files.
+        Args:
+            prompt_tokenizer (PromptTokenizingStrategy): The prompt tokenizing method for proccessing the data.
+            dataset (dataset.Dataset): Dataset with text files.
+    """
+
+    def __init__(  # pylint: disable=super-init-not-called
         self,
         prompt_tokenizer: PromptTokenizingStrategy,
         dataset: IterableDataset,
@@ -42,7 +51,7 @@ class ConstantLengthDataset(IterableDataset):
             seq_length (int): Length of token sequences to return.
     """
 
-    def __init__(
+    def __init__(  # pylint: disable=super-init-not-called
         self,
         tokenizer,
         datasets,