Instructions to use Team-ACE/EnvACE-Qwen3-1.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Team-ACE/EnvACE-Qwen3-1.7B with Transformers:

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

pipe = pipeline("text-generation", model="Team-ACE/EnvACE-Qwen3-1.7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Team-ACE/EnvACE-Qwen3-1.7B")
model = AutoModelForCausalLM.from_pretrained("Team-ACE/EnvACE-Qwen3-1.7B", 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 Team-ACE/EnvACE-Qwen3-1.7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Team-ACE/EnvACE-Qwen3-1.7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Team-ACE/EnvACE-Qwen3-1.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Team-ACE/EnvACE-Qwen3-1.7B

SGLang

How to use Team-ACE/EnvACE-Qwen3-1.7B 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 "Team-ACE/EnvACE-Qwen3-1.7B" \
    --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": "Team-ACE/EnvACE-Qwen3-1.7B",
		"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 "Team-ACE/EnvACE-Qwen3-1.7B" \
        --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": "Team-ACE/EnvACE-Qwen3-1.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Team-ACE/EnvACE-Qwen3-1.7B with Docker Model Runner:
```
docker model run hf.co/Team-ACE/EnvACE-Qwen3-1.7B
```

EnvACE-Qwen3-1.7B

Model Description

EnvACE-Qwen3-1.7B is a tool-interactive agent model based on Qwen/Qwen3-1.7B (Thinking Mode), trained with the EnvACE framework for long-horizon tool use. Instead of interacting with real or synthesized executable environments during training, the model is trained by world rehearsal: it internalizes environment dynamics in its own parameters and acts as its own environment.

Training Process

EnvACE replaces external environment interaction with world rehearsal inside a single policy:

Acting / rehearsal alternation: the policy first generates a tool call, then plays the role of the environment to produce the response induced by that action, and conditions its subsequent decisions on the rehearsed response.
Joint end-to-end optimization: both roles share one set of parameters and are trained together with role-wise GRPO (a separate advantage baseline per role, one shared policy) from task-success rewards only — a pure RL stage, with no external simulator or executable environment in the loop.
Agent world model: through rehearsal the policy internalizes the relationship between actions and environment responses, yielding a world model that directly supports decision making. At test time this enables private rehearsal before committed execution, giving further gains under a moderate rehearsal budget without additional external interaction.

The method is evaluated on BFCL-v4, τ²-Bench, VitaBench and FinMCP-Bench, where it shows strong and transferable performance against environment-scaling baselines; controlled studies show world rehearsal consistently improves policy learning across model scales. See the paper for full results.

How to Use

Basic Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Team-ACE/EnvACE-Qwen3-1.7B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Qwen3 chat template + native function-calling format:
# tokenizer.apply_chat_template(messages, tools=tools, add_generation_prompt=True)

Recommended sampling parameters (inherited from Qwen3): temperature=0.6, top_p=0.95, top_k=20.

With the EnvACE Framework

For training and for full integration with tool-interactive environments, see the EnvACE repository.

Related Resources

Paper: EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
Project page: https://within-yao.github.io/EnvACE/
Code: Within-yao/EnvACE
Collection: EnvACE models
Other Models:
- EnvACE-Qwen3-1.7B
- EnvACE-Qwen3-8B

Citation

If you use this model, please cite our work:

@article{xu2026envace,
  title={EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning},
  author={Xu, Zishan and Yao, Zhiyuan and Chen, Yuxin and Guo, Yifu and Lu, Zhengxi and Lu, Yuquan and Huang, Jinyang and Xu, Yan and Wang, Yasheng and Zhang, Weinan and Zeng, Xingshan and Liu, Weiwen},
  journal={arXiv preprint arXiv:2608.06197},
  year={2026}
}