Instructions to use dongguanting/ToolSpace-744B-A40B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dongguanting/ToolSpace-744B-A40B with Transformers:

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

pipe = pipeline("text-generation", model="dongguanting/ToolSpace-744B-A40B")
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-744B-A40B")
model = AutoModelForCausalLM.from_pretrained("dongguanting/ToolSpace-744B-A40B", 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-744B-A40B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dongguanting/ToolSpace-744B-A40B"
# 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-744B-A40B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dongguanting/ToolSpace-744B-A40B

SGLang

How to use dongguanting/ToolSpace-744B-A40B 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-744B-A40B" \
    --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-744B-A40B",
		"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-744B-A40B" \
        --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-744B-A40B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dongguanting/ToolSpace-744B-A40B with Docker Model Runner:
```
docker model run hf.co/dongguanting/ToolSpace-744B-A40B
```

ToolSpace-744B-A40B

Code · Evaluation · 8B · 35B-A3B · 744B-A40B

ToolSpace-744B-A40B is the GLM-5.2-based mixture-of-experts agent evaluated in the ToolSpace paper, with 744B total and 40B active parameters. This repository distributes the official Atria-Dawn full-release checkpoint.

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	GLM-5.2
Architecture	MoE, 744B total / 40B active parameters
Checkpoint	Official Atria-Dawn full release
Context length	512K, following the official release
Weight format	BF16 Safetensors

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.
GLM-5.2	29.3	56.7	43.4	37.1	75.6	13.3	56.9	44.6
ToolSpace-744B-A40B	54.7	67.8	57.5	43.3	78.4	27.5	67.1	56.6

Usage

Follow the official Atria-Dawn deployment guide for distributed SGLang or vLLM serving, using dongguanting/ToolSpace-744B-A40B as the model path. The BF16 checkpoint is approximately 1.51 TB.

Use the tokenizer, configuration, and chat template included in this repository.

Evaluation commands and benchmark configurations are available in the ToolSpace evaluation directory.

Downloads last month: 6

Safetensors

Model size

753B params

Tensor type

BF16

F32

Model tree for dongguanting/ToolSpace-744B-A40B

Base model

zai-org/GLM-5.2

Finetuned

(27)

this model

Collection including dongguanting/ToolSpace-744B-A40B

ToolSpace

Collection

The collection of ToolSpace • 3 items • Updated about 9 hours ago