Upload file README.md
This commit is contained in:
105
README.md
105
README.md
@@ -1,3 +1,106 @@
|
|||||||
---
|
---
|
||||||
license: apache-2.0
|
base_model:
|
||||||
|
- Qwen/Qwen3-8B
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
library_name: transformers
|
||||||
|
license: mit
|
||||||
|
tags:
|
||||||
|
- LLM
|
||||||
|
pipeline_tag: text-generation
|
||||||
---
|
---
|
||||||
|
# 🔍 WebExplorer-8B
|
||||||
|
|
||||||
|
<!-- [](https://huggingface.co/WebExplorer-8B)
|
||||||
|
[](https://arxiv.org/abs/xxxx.xxxxx) -->
|
||||||
|
|
||||||
|
A state-of-the-art 8B parameter web agent model designed for complex information-seeking tasks and long-horizon reasoning.
|
||||||
|
|
||||||
|
## 🌟 Overview
|
||||||
|
|
||||||
|
WebExplorer-8B is an advanced web navigation agent trained on **WebExplorer**-QA. The model demonstrates exceptional performance on challenging information-seeking benchmarks while maintaining efficiency with only 8 billion parameters.
|
||||||
|
|
||||||
|
## ✨ Key Features
|
||||||
|
|
||||||
|
- 🌐 **Long-horizon Reasoning**: Supports up to 128K context length and 100 tool calling turns
|
||||||
|
- 🛠️ **Tool Utilization**: Masters search and browse functionalities
|
||||||
|
- 🏆 **State-of-the-art Performance**: Achieves best-in-class results among models under 10B parameters
|
||||||
|
|
||||||
|
## 🏗️ Model Architecture
|
||||||
|
|
||||||
|
Built on Qwen3-8B base model and trained through a two-phase approach:
|
||||||
|
|
||||||
|
1. **Supervised Fine-tuning (SFT)**: Cold-start initialization with high-quality trajectories
|
||||||
|
2. **Reinforcement Learning (RL)**: Enhanced using GRPO algorithm with progressive context expansion
|
||||||
|
|
||||||
|
## 📊 Performance
|
||||||
|
|
||||||
|
WebExplorer-8B achieves state-of-the-art performance across multiple information-seeking benchmarks:
|
||||||
|
|
||||||
|
| Benchmark | Score |
|
||||||
|
|-----------|-------|
|
||||||
|
| BrowseComp-en | **15.7** |
|
||||||
|
| BrowseComp-zh | **32.0** |
|
||||||
|
| GAIA | **50.0** |
|
||||||
|
| WebWalkerQA | **62.7** |
|
||||||
|
| FRAMES | **75.7** |
|
||||||
|
| XBench-DeepSearch | **53.7** |
|
||||||
|
| HLE | **17.3** |
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
## 🛠️ Tool Schema
|
||||||
|
|
||||||
|
WebExplorer-8B supports two tools for web interaction:
|
||||||
|
|
||||||
|
### 1. Browse Tool
|
||||||
|
|
||||||
|
```json
|
||||||
|
{
|
||||||
|
"name": "browse",
|
||||||
|
"type": "function",
|
||||||
|
"description": "Extract specific information from a webpage",
|
||||||
|
"parameters": {
|
||||||
|
"type": "object",
|
||||||
|
"properties": {
|
||||||
|
"url": {
|
||||||
|
"type": "string",
|
||||||
|
"description": "Target URL to browse. The webpage content will be processed by the LLM for information extraction."
|
||||||
|
},
|
||||||
|
"query": {
|
||||||
|
"type": "string",
|
||||||
|
"description": "Specific query about the webpage content. The LLM will analyze the content to answer this query."
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"required": ["url", "query"]
|
||||||
|
}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### 2. Search Tool
|
||||||
|
|
||||||
|
```json
|
||||||
|
{
|
||||||
|
"name": "search",
|
||||||
|
"type": "function",
|
||||||
|
"description": "Perform web search queries",
|
||||||
|
"parameters": {
|
||||||
|
"type": "object",
|
||||||
|
"properties": {
|
||||||
|
"queries": {
|
||||||
|
"type": "array",
|
||||||
|
"items": {
|
||||||
|
"type": "string"
|
||||||
|
},
|
||||||
|
"description": "List of search queries. Returns search results containing title, URL, and snippet for each query."
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"required": ["queries"]
|
||||||
|
}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user