Improve model card: Add pipeline tag, project page, and update paper link

This PR enhances the model card for `Qwen3Guard-Stream-8B` by:
- Adding the `pipeline_tag: text-classification` to the metadata, which helps users discover this model more easily for safety classification tasks on the Hugging Face Hub.
- Updating the link to the Technical Report in the model card content to point to the official Hugging Face paper page: https://huggingface.co/papers/2510.14276.
- Adding the project's official blog page as `project_page` to the metadata, providing an additional valuable resource for users.

README.md

@@ -1,9 +1,11 @@
 ---
+base_model:
+- Qwen/Qwen3-8B
 library_name: transformers
 license: apache-2.0
 license_link: https://huggingface.co/Qwen/Qwen3Guard-Stream-8B/blob/main/LICENSE
-base_model:
-- Qwen/Qwen3-8B
+pipeline_tag: text-classification
+project_page: https://qwen.ai/blog?id=f0bbad0677edf58ba93d80a1e12ce458f7a80548&from=research.research-list
 ---
 
 # Qwen3Guard-Stream-8B
@@ -20,7 +22,7 @@ This repository hosts **Qwen3Guard-Stream**, which offers the following key adva
 *   **Three-Tiered Severity Classification:** Enables detailed risk assessment by categorizing outputs into safe, controversial, and unsafe severity levels, supporting adaptation to diverse deployment scenarios.
 *   **Multilingual Support:** Supports 119 languages and dialects, ensuring robust performance in global and cross-lingual applications.
 
-For more details, please refer to our [blog](https://qwen.ai/blog?id=f0bbad0677edf58ba93d80a1e12ce458f7a80548&from=research.research-list), [GitHub](https://github.com/QwenLM/Qwen3Guard), and [Technical Report](https://github.com/QwenLM/Qwen3/blob/main/Qwen3_Technical_Report.pdf).
+For more details, please refer to our [blog](https://qwen.ai/blog?id=f0bbad0677edf58ba93d80a1e12ce458f7a80548&from=research.research-list), [GitHub](https://github.com/QwenLM/Qwen3Guard), and [Technical Report](https://huggingface.co/papers/2510.14276).
 
 ## Quickstart
 
@@ -63,7 +65,8 @@ token_ids = model_inputs.input_ids[0]
 # In a real-world scenario, the user's input is processed completely before the model generates a response.
 token_ids_list = token_ids.tolist()
 # We identify the end of the user's turn in the tokenized input.
-# The template for a user turn is `<|im_start|>user\n...<|im_end|>`.
+# The template for a user turn is `<|im_start|>user
+...<|im_end|>`.
 im_start_token = '<|im_start|>'
 user_token = 'user'
 im_end_token = '<|im_end|>'