Instructions to use hkust-nlp/WebExplorer-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hkust-nlp/WebExplorer-8B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="hkust-nlp/WebExplorer-8B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hkust-nlp/WebExplorer-8B")
model = AutoModelForCausalLM.from_pretrained("hkust-nlp/WebExplorer-8B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hkust-nlp/WebExplorer-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hkust-nlp/WebExplorer-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hkust-nlp/WebExplorer-8B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/hkust-nlp/WebExplorer-8B

SGLang

How to use hkust-nlp/WebExplorer-8B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "hkust-nlp/WebExplorer-8B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hkust-nlp/WebExplorer-8B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "hkust-nlp/WebExplorer-8B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hkust-nlp/WebExplorer-8B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use hkust-nlp/WebExplorer-8B with Docker Model Runner:
```
docker model run hf.co/hkust-nlp/WebExplorer-8B
```

Junteng commited on Sep 8, 2025

Commit

98ed2f6

verified ·

1 Parent(s): 5a07909

Upload file README.md

Browse files

Files changed (1) hide show

README.md +106 -3

README.md CHANGED Viewed

@@ -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
+<!-- [![Model](https://img.shields.io/badge/Model-8B_Parameters-blue)](https://huggingface.co/WebExplorer-8B)
+[![Paper](https://img.shields.io/badge/Paper-arXiv-red)](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"]
+    }
+}
+```