Improve model card: Add pipeline tag, library name, paper link, relevant tags, and sample usage

README.md

@@ -1,11 +1,24 @@
 ---
-license: apache-2.0
-datasets:
-- inclusionAI/ASearcher-train-data
 base_model:
 - Qwen/QwQ-32B
+datasets:
+- inclusionAI/ASearcher-train-data
+license: apache-2.0
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- agent
+- search
+- qwen
 ---
 
+# ASearcher-Web-QwQ-32B
+
+This model is presented in the paper [Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL](https://huggingface.co/papers/2508.07976).
+
+**Paper**: [https://huggingface.co/papers/2508.07976](https://huggingface.co/papers/2508.07976)
+**Code**: [https://github.com/inclusionAI/ASearcher](https://github.com/inclusionAI/ASearcher)
+
 ### Instruction
 [![GitHub](https://img.shields.io/badge/GitHub-Repository-black?logo=github)](https://github.com/inclusionAI/ASearcher)
 
@@ -37,4 +50,34 @@ We have released multiple models trained with different settings and based on fo
 We also release our full [training data](https://huggingface.co/datasets/inclusionAI/ASearcher-train-data) and [test data](https://huggingface.co/datasets/inclusionAI/ASearcher-test-data), you can easily get them and reproduce our result.
 
 ### Quickstart
-If you want to learn more details, please refer to our GitHub repository: [ASearcher](https://github.com/inclusionAI/ASearcher)
+
+To perform text generation with `ASearcher-Web-QwQ-32B` using the `transformers` library, you can use the following code:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_name = "inclusionAI/ASearcher-Web-QwQ-32B"
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+
+messages = [
+    {"role": "user", "content": "What is the capital of France?"},
+]
+
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    model_inputs.input_ids,
+    max_new_tokens=512
+)
+generated_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(generated_text)
+```
+For more details and advanced usage, please refer to our GitHub repository: [ASearcher](https://github.com/inclusionAI/ASearcher)