Update README.md

README.md

@@ -430,7 +430,7 @@ python3 train.py \
 ```
 
 # 3. Finetuning
-To finally finetune your model to answer your questions, run this code to prepare your data:
+To finetune your model to answer your questions, run this code to prepare the finetuning data:
 ```python
 import os
 import numpy as np
@@ -676,7 +676,6 @@ if __name__ == "__main__":
 
 # 5. Our training results
 ## 5.1 Pretraining results
-
 We did the pretraining on a single RTX 5060 Ti 16GB for 30,000 iterations for ~3 days.
 Out final `val loss` value was **3.0450** and our final `train loss` was **3.0719**.
 
@@ -692,6 +691,13 @@ We tested our finetuned model a lot:
    --> Answer:
 2. ...
 
+# 7. Thanks to...
+1. Andrej Karpathy for his nanoGPT Code and his YouTube Videos in the make-mode-series
+2. HugginfaceTW for the Fineweb-Edu-10BT-Sample Training Dataset
+3. Yahma for the alpaca-cleaned dataset for the finetuning
+4. My dad for his support
+5. My GPU for training and running my new model ;-)
+
 ---
 license: apache-2.0
 datasets: