Update README.md

README.md

@@ -16,6 +16,8 @@ model-index:
       name: pass@1
       verified: false
 ---
+## Please note this model is a test, the full finetuned version can be found here: https://huggingface.co/rombodawg/Llama-3-8B-Instruct-Coder
+_______________________________________________________
 ## GOOGLE COLAB IS A SCAM DO NOT USE THE PAID VERSION
 ## THEY WILL DISCONNECT YOUR RUNTIME BEFORE EVEN 24 HOURS
 https://github.com/googlecolab/colabtools/issues/3451
@@ -66,6 +68,7 @@ import torch
 major_version, minor_version = torch.cuda.get_device_capability()
 # Must install separately since Colab has torch 2.2.1, which breaks packages
 !pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
+
 if major_version >= 8:
     # Use this for new GPUs like Ampere, Hopper GPUs (RTX 30xx, RTX 40xx, A100, H100, L40)
     !pip install --no-deps packaging ninja einops flash-attn xformers trl peft accelerate bitsandbytes