Update README.md

README.md

@@ -13,8 +13,6 @@ model-index:
 
 ![Kunou](https://huggingface.co/Sao10K/72B-Qwen2.5-Kunou-v1/resolve/main/knn.png)
 
-**Sister Versions for Lightweight and Heavyweight Use!**
-
 # 14B-Qwen2.5-Freya-v1
 
 I decided to mess around with training methods, considering the re-emegence of no longer used methods like multi-step training. Some people began doing it again, and so, why not? Inspired by LimaRP's methology but done it my way.
@@ -31,8 +29,8 @@ Freya-S2
 Recommended Model Settings | *Look, I just use these, they work fine enough. I don't even know how DRY or other meme samplers work. Your system prompt matters more anyway.*
 ```
 Prompt Format: ChatML
-Temperature: 1.1
-min_p: 0.1
+Temperature: 1+ # I don't know, man.
+min_p: 0.05
 ```
 
 Training time in total was ~10 Hours on a 8xH100 Node, sponsored by the Government of Singapore or something. Thanks for the national service allowance, MHA.
@@ -118,7 +116,7 @@ liger_fused_linear_cross_entropy: true
 
 # Iterations
 num_epochs:
-- s1: 2
+- s1: 1
 - s2: 2
 
 # Sampling