Add `conversational` tag

Adding this tag will mark the model as `conversational` which will make it more discoverable on the Hub, and especially ready-to-use with the Chat Completion API in Inference Providers.

> This release does not include a Jinja-format chat template. Please refer to the Python code mentioned above.

Usually the `conversational` tag is auto-generated by the Hub when a jinja-style chat template exists in the repo. Hence why it's best to hardcode the tag for now.

README.md

@@ -4,6 +4,8 @@ library_name: transformers
 base_model:
   - deepseek-ai/DeepSeek-V3.2-Exp-Base
 base_model_relation: finetune
+tags:
+  - conversational
 ---
 # DeepSeek-V3.2: Efficient Reasoning & Agentic AI