Instructions to use Intelligent-Internet/II-Search-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Intelligent-Internet/II-Search-4B with Transformers:

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

pipe = pipeline("text-generation", model="Intelligent-Internet/II-Search-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Intelligent-Internet/II-Search-4B")
model = AutoModelForCausalLM.from_pretrained("Intelligent-Internet/II-Search-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
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 Intelligent-Internet/II-Search-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Intelligent-Internet/II-Search-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Intelligent-Internet/II-Search-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Intelligent-Internet/II-Search-4B

SGLang

How to use Intelligent-Internet/II-Search-4B 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 "Intelligent-Internet/II-Search-4B" \
    --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": "Intelligent-Internet/II-Search-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Intelligent-Internet/II-Search-4B" \
        --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": "Intelligent-Internet/II-Search-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Intelligent-Internet/II-Search-4B with Docker Model Runner:
```
docker model run hf.co/Intelligent-Internet/II-Search-4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

II-Search-4B

Model Description

II-Search-4B is a 4B parameter language model based on Qwen3-4B, fine-tuned specifically for information seeking tasks and web-integrated reasoning. It excels at complex multi-hop information retrieval, fact verification, and comprehensive report generation.

Key Features

Enhanced tool usage for web search and webpage visits
Multi-hop reasoning capabilities with sophisticated planning
Verified information retrieval with cross-checking
Strong performance on factual QA benchmarks
Comprehensive report generation for research queries

Training Methodology

Our training process consisted of three key phases:

Phase 1: Tool Call Ability Stimulation

We used a distillation approach from larger models (Qwen3-235B) to generate reasoning paths with function calling on multi-hop datasets. This established the base capabilities for tool use.

Phase 2: Reasoning Improvement

We addressed initial limitations by:

Creating synthetic problems requiring more reasoning turns, inspired by Random Walk algorithm
Improving reasoning thought patterns for more efficient and cleaner reasoning paths

Phase 3: Rejection Sampling & Report Generation

We applied:

Filtering to keep only high-quality reasoning traces (correct answers with proper reasoning)
STORM-inspired techniques to enhance comprehensive report generation

Phase 4: Reinforcement Learning

We trained the model using reinforcement learning

Used dataset: dgslibisey/MuSiQue
Incorporated our in-house search database (containing Wiki data, Fineweb data, and ArXiv data)

Performance

Benchmark	Qwen3-4B	Jan-4B	WebSailor-3B	II-Search-4B
OpenAI/SimpleQA	76.8	80.1	81.8	91.8
Google/Frames	30.7	24.8	34.0	67.5
Seal_0	6.31	2.7	1.8	22.5

Tool Usage Comparison

Simple QA (SerpDev)

	Qwen3-4B	Jan-4B	WebSailor-3B	II-Search-4B
# Search	1.0	0.9	2.1	2.2
# Visit	0.1	1.9	6.4	3.5
# Total Tools	1.1	2.8	8.5	5.7

All benchmark traces from models can be found at: https://huggingface.co/datasets/Intelligent-Internet/II-Search-Benchmark-Details

Intended Use

II-Search-4B is designed for:

Information seeking and factual question answering
Research assistance and comprehensive report generation
Fact verification and evidence-based reasoning
Educational and research applications requiring factual accuracy

Usage

To deploy and interact with the II-Search-4B model effectively, follow these options:

Serve the model using vLLM or SGLang

Use the following command to serve the model with vLLM (adjust parameters as needed for your hardware setup):

vllm serve Intelligent-Internet/II-Search-4B --served-model-name II-Search-4B --tensor-parallel-size 8 --enable-reasoning --reasoning-parser deepseek_r1 --rope-scaling '{"rope_type":"yarn","factor":1.5,"original_max_position_embeddings":98304}' --max-model-len 131072

This configuration enables distributed tensor parallelism across 8 GPUs, reasoning capabilities, custom RoPE scaling for extended context, and a maximum context length of 131,072 tokens.

Integrate web_search and web_visit tools

Equip the served model with web_search and web_visit tools to enable internet-aware functionality. Alternatively, use a middleware like MCP for tool integration—see this example repository: https://github.com/hoanganhpham1006/mcp-server-template.

Host on macOS with MLX for local use

As an alternative for Apple Silicon users, host the quantized II-Search-4B-MLX version on your Mac. Then, interact with it via user-friendly interfaces like LM Studio or Ollama Desktop.

Recommended Generation Parameters

generate_cfg = {
    'top_k': 20,
    'top_p': 0.95,
    'temperature': 0.6,
    'repetition_penalty': 1.1,
    'max_tokens': 2048
}

For a query that you need to find a short and accurate answer. Add the following phrase: "\n\nPlease reason step-by-step and put the final answer within \\boxed{}."

Citation

@misc{II-Search-4B,
  author = {Intelligent Internet},
  title = {II-Search-4B: Information Seeking and Web-Integrated Reasoning LLM},
  year = {2025},
  publisher = {Hugging Face},
  journal = {Hugging Face Hub},
  howpublished = {\url{https://huggingface.co/II-Vietnam/II-Search-4B}},
}

Downloads last month: 66

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for Intelligent-Internet/II-Search-4B

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B