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

Libraries

How to use dongguanting/ToolSpace-8B with Transformers:

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

pipe = pipeline("text-generation", model="dongguanting/ToolSpace-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dongguanting/ToolSpace-8B")
model = AutoModelForCausalLM.from_pretrained("dongguanting/ToolSpace-8B", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dongguanting/ToolSpace-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dongguanting/ToolSpace-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": "dongguanting/ToolSpace-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dongguanting/ToolSpace-8B

SGLang

How to use dongguanting/ToolSpace-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 "dongguanting/ToolSpace-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": "dongguanting/ToolSpace-8B",
		"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 "dongguanting/ToolSpace-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": "dongguanting/ToolSpace-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dongguanting/ToolSpace-8B with Docker Model Runner:
```
docker model run hf.co/dongguanting/ToolSpace-8B
```

dongguanting commited on 6 days ago

Commit

ba82d32

verified ·

1 Parent(s): 1ad06f8

Add ToolSpace model card and paper results

Browse files

Files changed (1) hide show

README.md +57 -0

README.md CHANGED Viewed

@@ -1,3 +1,60 @@
 ---
 license: mit
 ---

 ---
 license: mit
+base_model: Qwen/Qwen3-8B
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- agent
+- tool-use
+- function-calling
+- long-horizon
+- toolspace
+- reinforcement-learning
 ---
+# ToolSpace-8B
+[Code](https://github.com/dongguanting/ToolSpace) · [Evaluation](https://github.com/dongguanting/ToolSpace/tree/main/evaluation) · [8B](https://huggingface.co/dongguanting/ToolSpace-8B) · [35B-A3B](https://huggingface.co/dongguanting/ToolSpace-35B-A3B) · [744B-A40B](https://huggingface.co/dongguanting/ToolSpace-744B-A40B)
+ToolSpace-8B is a Qwen3-8B agent model trained with ToolSpace trajectories and on-policy agent reinforcement learning for long-horizon tool use.
+ToolSpace constructs a tool-composition graph from real execution traces, capturing data, state, and retry dependencies. It synthesizes cross-environment tasks through state-aware walks with rollback and keeps trajectories that pass execution-based verification.
+**Paper:** *ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents*.
+## Model information
+| Item | Details |
+| --- | --- |
+| Backbone | Qwen3-8B |
+| Architecture | Dense, 8B parameters |
+| Context length | 65,536 tokens |
+| Weight format | BF16 Safetensors |
+| Training | Supervised fine-tuning + agent RL |
+## Results
+Results from Table 1 of the ToolSpace paper. Avg. is the unweighted mean over the seven benchmarks.
+| Model | AutomationBench | SkillsBench | JobBench | τ³-Bench Banking | BFCL V4 | Harvey LAB | OfficeQA Pro | Avg. |
+| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
+| Qwen3-8B | 0.0 | 0.1 | 0.1 | 4.1 | 42.8 | 0.0 | 3.0 | 7.2 |
+| ToolSpace-8B (SFT) | 32.3 | 3.9 | 13.1 | 10.3 | 65.3 | 0.0 | 12.0 | 19.6 |
+| **ToolSpace-8B + Agent RL (this checkpoint)** | 34.3 | 4.1 | 15.5 | 11.3 | 67.5 | 0.0 | 12.0 | 20.7 |
+## Usage
+Serve with vLLM and the included chat template:
+```bash
+vllm serve dongguanting/ToolSpace-8B \
+  --served-model-name ToolSpace-8B \
+  --max-model-len 65536 \
+  --enable-auto-tool-choice \
+  --tool-call-parser hermes \
+  --reasoning-parser deepseek_r1
+```
+The server exposes an OpenAI-compatible endpoint at `http://localhost:8000/v1`.
+Evaluation commands and benchmark configurations are available in the [ToolSpace evaluation directory](https://github.com/dongguanting/ToolSpace/tree/main/evaluation).