solve bug

GUIDE.md

@@ -305,7 +305,7 @@ from xllm.datasets import BaseDataset
 
 In each new dataset, we must implement two methods:
 
-- get_data
+- get_data (classmethod)
 - get_sample
 
 Let's start implementing new dataset
@@ -320,6 +320,7 @@ from xllm.types import RawSample
 
 class MyDataset(BaseDataset):
 
+    @classmethod
     def get_data(cls, config: Config) -> Optional[Tuple[List[RawSample], Optional[List[RawSample]]]]:
         ...
 
@@ -332,6 +333,8 @@ class MyDataset(BaseDataset):
 The input values of this method are cls from `MyDataset` and `Config`. By default, the default config from `xllm` is
 used: `from xllm import Config`
 
+It's a `classmethod`, so you can use it without creating an instance of the class.
+
 The `get_data` method should return a tuple of two elements: **training data** and **eval data**. These data should be
 lists of type `RawSample`. `RawSample`, in turn, is simply an alias for the following
 type: `Dict[str, Union[str, int, float, List[str]]]`. In other words, each sample in the data should be a dictionary,
@@ -838,3 +841,13 @@ details, you can refer to this source: https://github.com/Dao-AILab/flash-attent
 **Q:** Can I use `bitsandbytes int4`, `bitsandbytes int8` and `gptq model` at once?  
 **A:** You can choose either `bitsandbytes int4` or `bitsandbytes int8` only. Training through the gptq model is not
 recommended, but it is supported. Your model must already be converted to the GPTQ format.
+
+## Tale Quest
+
+`Tale Quest` is my personal project which was built using `xllm` and `Shurale`. It's an interactive text-based game
+in `Telegram` with dynamic AI characters, offering infinite scenarios
+
+You will get into exciting journeys and complete fascinating quests. Chat
+with `George Orwell`, `Tech Entrepreneur`, `Young Wizard`, `Noir Detective`, `Femme Fatale` and many more
+
+Try it now: [https://t.me/talequestbot](https://t.me/TaleQuestBot?start=Z2g)

README.md

@@ -632,7 +632,7 @@ in `Telegram` with dynamic AI characters, offering infinite scenarios
 You will get into exciting journeys and complete fascinating quests. Chat
 with `George Orwell`, `Tech Entrepreneur`, `Young Wizard`, `Noir Detective`, `Femme Fatale` and many more
 
-Try it now: [https://t.me/talequestbot](https://t.me/PapayaAIBot?start=Z2g)
+Try it now: [https://t.me/talequestbot](https://t.me/TaleQuestBot?start=Z2g)
 
 ### Please support me here
 

examples/README.md

@@ -1,5 +1,28 @@
 # Examples of using XLLM
 
-## Demo project
-
 ## Minimal example
+
+`minimal_using`
+
+## Minimal example using CLI
+
+`minimal_using_cli`
+
+## Notebooks
+
+| Name                                      | Comment                                                                            | Link                                                                                                                                                                   |
+|-------------------------------------------|------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| X—LLM Prototyping                         | In this notebook you will learn the basics of the library                          | [![xllm_prototyping](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1zsNmJFns1PKZy5VE5p5nsQL-mZF7SwHf?usp=sharing) |
+| Llama2 & Mistral AI efficient fine-tuning | 7B model training in colab using QLoRA, bnb int4, gradient checkpointing and X—LLM | [![Llama2MistalAI](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1CNNB_HPhQ8g7piosdehqWlgA30xoLauP?usp=sharing)   |
+
+## Useful materials
+
+- [X—LLM Repo](https://github.com/BobaZooba/xllm): main repo of the `xllm` library
+- [Quickstart](https://github.com/KompleteAI/xllm/tree/docs-v1#quickstart-): basics of `xllm`
+- [Examples](https://github.com/BobaZooba/xllm/examples): minimal examples of using `xllm`
+- [Guide](https://github.com/BobaZooba/xllm/blob/main/GUIDE.md): here, we go into detail about everything the library can
+  do
+- [Demo project](https://github.com/BobaZooba/xllm-demo): here's a minimal step-by-step example of how to use X—LLM and fit it
+  into your own project
+- [WeatherGPT](https://github.com/BobaZooba/wgpt): this repository features an example of how to utilize the xllm library. Included is a solution for a common type of assessment given to LLM engineers, who typically earn between $120,000 to $140,000 annually
+- [Shurale](https://github.com/BobaZooba/shurale): project with the finetuned 7B Mistal model

examples/notebooks/Llama2_&_Mistral_AI_efficient_fine_tuning_using_QLoRA,_bnb_int4,_gradient_checkpointing_and_X—LLM_🦖.ipynb

@@ -1843,7 +1843,7 @@
         "You will get into exciting journeys and complete fascinating quests. Chat\n",
         "with `George Orwell`, `Tech Entrepreneur`, `Young Wizard`, `Noir Detective`, `Femme Fatale` and many more\n",
         "\n",
-        "Try it now: [https://t.me/talequestbot](https://t.me/PapayaAIBot?start=Z2g)"
+        "Try it now: [https://t.me/talequestbot](https://t.me/TaleQuestBot?start=Z2g)"
       ],
       "metadata": {
         "id": "Oz4LrVcZlE6P"

examples/notebooks/🦖_X—LLM_Prototyping.ipynb

@@ -2711,7 +2711,7 @@
         "You will get into exciting journeys and complete fascinating quests. Chat\n",
         "with `George Orwell`, `Tech Entrepreneur`, `Young Wizard`, `Noir Detective`, `Femme Fatale` and many more\n",
         "\n",
-        "Try it now: [https://t.me/talequestbot](https://t.me/PapayaAIBot?start=Z2g)"
+        "Try it now: [https://t.me/talequestbot](https://t.me/TaleQuestBot?start=Z2g)"
       ],
       "metadata": {
         "id": "5wJJrKnglAkK"