Instructions to use mis2/Trajectory2Gym-30B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mis2/Trajectory2Gym-30B-A3B with Transformers:

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

pipe = pipeline("text-generation", model="mis2/Trajectory2Gym-30B-A3B")
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("mis2/Trajectory2Gym-30B-A3B")
model = AutoModelForCausalLM.from_pretrained("mis2/Trajectory2Gym-30B-A3B", 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 mis2/Trajectory2Gym-30B-A3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mis2/Trajectory2Gym-30B-A3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mis2/Trajectory2Gym-30B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mis2/Trajectory2Gym-30B-A3B

SGLang

How to use mis2/Trajectory2Gym-30B-A3B 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 "mis2/Trajectory2Gym-30B-A3B" \
    --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": "mis2/Trajectory2Gym-30B-A3B",
		"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 "mis2/Trajectory2Gym-30B-A3B" \
        --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": "mis2/Trajectory2Gym-30B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mis2/Trajectory2Gym-30B-A3B with Docker Model Runner:
```
docker model run hf.co/mis2/Trajectory2Gym-30B-A3B
```

Trajectory2Gym-30B-A3B

Full-parameter supervised post-training for decision-grounded tool use. This checkpoint is the paper's corresponding scale, not a support-depth or component-ablation model.

Reported evaluation

Tau1	Tau2	BFCL three-group Overall
66.78	84.17	80.93

These are recorded paper results, not a fresh benchmark rerun during publication. Tau scores are domain macro averages. Tau1 Airline uses the disclosed seen-task protocol. Tau2 uses the official train/test split, and BFCL Overall equally averages Non-live, Live and Multi-turn groups.

Use

Use the included tokenizer and native tool schema format with non-thinking generation. For Qwen3 templates supporting it, pass enable_thinking=False to apply_chat_template. The 30B-A3B Instruct-2507 model retains its own native template; do not inject an 8B-specific prefix.

from transformers import AutoTokenizer, AutoModelForCausalLM
repo = 'mis2/Trajectory2Gym-30B-A3B'
tokenizer = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype='auto', device_map='auto')

Loading requires hardware memory appropriate to the scale and stored dtype. This release preserves the archived safetensor bytes: bfloat16. No quantization, retraining or numeric conversion was performed for release.

The public candidate corpus is not the exact rendered training view. The 30B-A3B model uses an expanded corpus. Model behavior and benchmark scores depend on the native interfaces, simulator and evaluation settings; this card does not claim cross-protocol equivalence.

Integrity and license

Weight files total 61,066,577,728 bytes. The source training-view SHA-256 is d739e4ea0a37fb92b766bdc48d4aab6123a92e8658d7a6ed10c20f64f7c55fc6. RELEASE_MANIFEST.json provides per-file checksums and archive-byte verification details. Internal source paths, credentials, optimizer states, training arguments and raw logs are excluded. Only non-inference path metadata may be removed from JSON configurations, as recorded in the manifest.

Apache-2.0; the base model's license is retained as LICENSE. Tool execution should use permissioned environments and independent authorization for high-impact actions.