Update src/content/docs/workers-ai/features/fine-tunes/loras.mdx

Co-authored-by: Kevin Jain <[email protected]>

Author: daisyfaithauma

src/content/docs/workers-ai/features/fine-tunes/loras.mdx

@@ -30,7 +30,7 @@ Workers AI supports fine-tuned inference with adapters trained with [Low-Rank Ad
   - `@cf/google/gemma-3-12b-it`
 
 - Adapter must be trained with rank `r <=8` as well as larger ranks if up to 32. You can check the rank of a pre-trained LoRA adapter through the adapter's `config.json` file
-- LoRA adapter file must be < 500MB
+- LoRA adapter file must be < 300MB
 - LoRA adapter files must be named `adapter_config.json` and `adapter_model.safetensors` exactly
 - You can test up to 30 LoRA adapters per account