---
library_name: transformers
pipeline_tag: text-generation
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE
language:
- en
base_model: Qwen/Qwen3-8B
base_model_relation: finetune
tags:
- search-agent
- tool-use
- function-calling
- deep-search
- qwen
---

# SearchQwen3-8B

**SearchQwen3-8B** is a compact Search Agent model from the Alibaba Cloud PAI team. It is trained with environment-aligned, solver-verified search trajectories generated by [EasyDistill 2.0](https://github.com/modelscope/easydistill/tree/v2.0.0), and is designed for multi-hop search, browsing, and evidence integration.

> SearchQwen3-8B 是基于 EasyDistill 2.0 环境对齐轨迹蒸馏链路训练的 Search Agent 小模型，支持结构化 `search` / `browse` 工具调用。

## Model overview

| Item | Value |
|---|---|
| Base model | [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) |
| Parameters | 8.19B |
| Context length | 40,960 |
| Recommended interface | Structured Tool-Call |
| Training data | [SynSearch-Data](https://huggingface.co/datasets/alibaba-pai/SynSearch-Data) |

## Results

LLM-judge accuracy (%). Multi-hop QA averages 2WikiMultiHopQA, Bamboogle, HotpotQA, and MuSiQue; Deep Search averages GAIA, WebWalkerQA, xbench-deepsearch, and BrowseComp-ZH.

| Interaction | Model | Deep Search | Overall |
|---|---|---:|---:|
| Tool-Call | Qwen3-8B | 24.50 | 40.31 |
| Tool-Call | **SearchQwen3-8B** | **35.42** | **50.31** |

## Quickstart

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "alibaba-pai/SearchQwen3-8B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
).eval()

messages = [
    {"role": "system", "content": "You are a search agent. Use tools before answering."},
    {"role": "user", "content": "Which city is the birthplace of the author of The Old Man and the Sea?"},
]
tools = [
    {
        "type": "function",
        "function": {
            "name": "search",
            "description": "Search the web.",
            "parameters": {
                "type": "object",
                "properties": {"query": {"type": "string"}},
                "required": ["query"],
            },
        },
    }
]

inputs = tokenizer.apply_chat_template(
    messages,
    tools=tools,
    add_generation_prompt=True,
    tokenize=True,
    return_tensors="pt",
    return_dict=True,
    enable_thinking=False,
).to(model.device)

output = model.generate(**inputs, max_new_tokens=256, do_sample=False)
print(tokenizer.decode(output[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=False))
```

The model returns a structured `<tool_call>`; execute the tool, append its response, and continue until a final answer is produced. An external search/browse backend is required.

## Related resources

- Framework: [EasyDistill 2.0](https://github.com/modelscope/easydistill/tree/v2.0.0)
- Data: [SynSearch-Data](https://huggingface.co/datasets/alibaba-pai/SynSearch-Data)

## License

This model follows the license included in this repository and the terms of its base model. Checksums are provided in `SHA256SUMS`.