make the readme easier to read

README.md

@@ -4,13 +4,7 @@ license: unknown
 
 ## Merging models like lego blocks using ddare and ties
 
-If you want to fine-tune, here's an example Unsloth fine tuning guide for:
-
-- [Alpaca + TinyLlama + RoPE Scaling full example.ipynb](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing#scrollTo=LjY75GoYUCB8)
-
-## How do I generate my own model merges?
-
-The code below merges the following HuggingFace TinyLlama models:
+This model was merged with the following HuggingFace TinyLlama models using ties:
 
 - TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
 - Doctor-Shotgun/TinyLlama-1.1B-32k-Instruct
@@ -18,6 +12,16 @@ The code below merges the following HuggingFace TinyLlama models:
 - Tensoic/TinyLlama-1.1B-3T-openhermes
 - Josephgflowers/TinyLlama-3T-Cinder-v1.3
 
+## How do I fine-tune this model?
+
+Please refer to the Unsloth fine-tuning guide for:
+
+- [Alpaca + TinyLlama + RoPE Scaling full example.ipynb](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing)
+
+## How do I generate my own model merges?
+
+Here's the standalone python script we used with logs below:
+
 ```python3
 import transformers
 import torch