Update openai.md (huggingface#1730)

I was able to set multimodal: 'true' when using a open ai backend running Qwen2-VL in a vllm openai like backend

Author: JeanBaptiste-dlb

docs/source/configuration/models/providers/openai.md

@@ -3,7 +3,7 @@
 | Feature                     | Available |
 | --------------------------- | --------- |
 | [Tools](../tools)           | No        |
-| [Multimodal](../multimodal) | No        |
+| [Multimodal](../multimodal) | Yes       |
 
 Chat UI can be used with any API server that supports OpenAI API compatibility, for example [text-generation-webui](https://github.com/oobabooga/text-generation-webui/tree/main/extensions/openai), [LocalAI](https://github.com/go-skynet/LocalAI), [FastChat](https://github.com/lm-sys/FastChat/blob/main/docs/openai_api.md), [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), and [ialacol](https://github.com/chenhunghan/ialacol) and [vllm](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html).