Update fine-tuning-ui-guide.mdx

fern/docs/text-gen-solution/fine-tuning-ui-guide.mdx

@@ -12,7 +12,7 @@ This tutorial will guide you through the process of fine-tuning a Large Language
 2. Start a text generation fine-tuning job.
 3. Inference with your fine-tuned LoRA asset.
 
-OctoAI supports LoRA fine-tuning for Llama-3.1-8B-Instruct (8K token context limit) and  Llama-3.1-70B-Instruct (8K token context limit). We encourage you to try Llama 3.1 8B first and try 70B with a smaller dataset (<1000 examples).
+OctoAI supports LoRA fine-tuning for Llama-3.1-8B-Instruct and  Llama-3.1-70B-Instruct (contact us for access) with 8K token context limit.
 
 ## 1. Prepare Your Datasets