Instructions to use MidTool/Arctic-MidTool-RL-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MidTool/Arctic-MidTool-RL-4B with Transformers:

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

pipe = pipeline("text-generation", model="MidTool/Arctic-MidTool-RL-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MidTool/Arctic-MidTool-RL-4B")
model = AutoModelForCausalLM.from_pretrained("MidTool/Arctic-MidTool-RL-4B", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MidTool/Arctic-MidTool-RL-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MidTool/Arctic-MidTool-RL-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": "MidTool/Arctic-MidTool-RL-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MidTool/Arctic-MidTool-RL-4B

SGLang

How to use MidTool/Arctic-MidTool-RL-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 "MidTool/Arctic-MidTool-RL-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": "MidTool/Arctic-MidTool-RL-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 "MidTool/Arctic-MidTool-RL-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": "MidTool/Arctic-MidTool-RL-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MidTool/Arctic-MidTool-RL-4B with Docker Model Runner:
```
docker model run hf.co/MidTool/Arctic-MidTool-RL-4B
```

Arctic-MidTool-RL-4B / README.md

fqjiang

initial release

38b5e74 3 days ago

preview code

Raw

History Blame Contribute Delete

2.24 kB

	---
	license: apache-2.0
	base_model:
	- MidTool/Arctic-MidTool-MT-4B
	library_name: transformers
	pipeline_tag: text-generation
	datasets:
	- MidTool/MidTool-Mix
	tags:
	- agentic
	- tool-use
	- function-calling
	- reinforcement-learning
	extra_gated_heading: Access this model
	extra_gated_prompt: >-
	By requesting access you agree to the Apache-2.0 license, and to the terms of the
	MidTool-Mix dataset this model was trained on
	(https://huggingface.co/datasets/MidTool/MidTool-Mix/blob/main/LICENSE). The model is
	provided as is, without warranty of any kind. The authors accept no liability for its
	outputs or for any use made of it.
	extra_gated_button_content: Agree and access
	---

	# Arctic-MidTool-RL-4B

	The final 4B agent from the MidTool recipe: `Qwen3-4B-Base` → mid-training on [MidTool-Mix](https://huggingface.co/datasets/MidTool/MidTool-Mix) → tool-use SFT → agentic RL. Start here if you want a model to run, rather than one to train further ([Arctic-MidTool-MT-4B](https://huggingface.co/MidTool/Arctic-MidTool-MT-4B) is the mid-training checkpoint).

	## Results

	\| 4B model \| BFCLv3 Overall \| τ²-Bench Pass@1 \| MCP-Universe Score \|
	\|---\|---\|---\|---\|
	\| Qwen3-4B (official) \| 24.27 \| 11.87 \| 16.05 \|
	\| Qwen3-4B-Base + SFT + RL \| 39.51 \| 13.04 \| 17.65 \|
	\| Arctic-MidTool-RL-4B \| 54.18 \| 19.96 \| 19.73 \|

	Largest gains are on multi-turn BFCL (27.63 vs 19.00) and τ²-Bench retail/airline — the settings that need long-horizon execution and recovery.

	Tool calls are emitted in the Qwen3 `<tool_call>` format; pass your schemas via the `tools=` argument of the chat template. Thinking mode is disabled in our evaluation setup.

	## Details

	Mid-trained on [MidTool-Mix](https://huggingface.co/datasets/MidTool/MidTool-Mix); see the dataset's [`LICENSE`](https://huggingface.co/datasets/MidTool/MidTool-Mix/blob/main/LICENSE) for data terms.

	See our paper for the full data, training, and evaluation details.

	```bibtex
	@article{jiang2026midtool,
	title = {MidTool: Mid-training Data Synthesis for Agentic Tool Use},
	author = {Jiang, Fengqing and Wang, Yite and Liu, Boyi and Wang, Zhaoyang and
	Xu, Canwen and Yao, Zhewei and Poovendran, Radha and He, Yuxiong},
	year = {2026}
	}
	```