[Workers AI]loras limits (#21608)

* loras limits

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

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

---------

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

Author: 2 people

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

@@ -18,12 +18,19 @@ Workers AI supports fine-tuned inference with adapters trained with [Low-Rank Ad
 ## Limitations
 
 - We only support LoRAs for the following models (must not be quantized):
-  - `@cf/meta-llama/llama-2-7b-chat-hf-lora`
-  - `@cf/mistral/mistral-7b-instruct-v0.2-lora`
-  - `@cf/google/gemma-2b-it-lora`
-  - `@cf/google/gemma-7b-it-lora`
-- Adapter must be trained with rank `r <=8`. You can check the rank of a pre-trained LoRA adapter through the adapter's `config.json` file
-- LoRA adapter file must be < 100MB
+
+  - `@cf/meta/llama-3.2-11b-vision-instruct`
+  - `@cf/meta/llama-3.3-70b-instruct-fp8-fast`
+  - `@cf/meta/llama-guard-3-8b`
+  - `@cf/meta/llama-3.1-8b-instruct-fast (soon)`
+  - `@cf/deepseek-ai/deepseek-r1-distill-qwen-32b`
+  - `@cf/qwen/qwen2.5-coder-32b-instruct`
+  - `@cf/qwen/qwq-32b`
+  - `@cf/mistralai/mistral-small-3.1-24b-instruct`
+  - `@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 < 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