Instructions to use FrontisAI/Frontis-MA1-30B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FrontisAI/Frontis-MA1-30B-SFT with Transformers:

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

pipe = pipeline("text-generation", model="FrontisAI/Frontis-MA1-30B-SFT")
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("FrontisAI/Frontis-MA1-30B-SFT")
model = AutoModelForCausalLM.from_pretrained("FrontisAI/Frontis-MA1-30B-SFT", 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 FrontisAI/Frontis-MA1-30B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FrontisAI/Frontis-MA1-30B-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FrontisAI/Frontis-MA1-30B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FrontisAI/Frontis-MA1-30B-SFT

SGLang

How to use FrontisAI/Frontis-MA1-30B-SFT 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 "FrontisAI/Frontis-MA1-30B-SFT" \
    --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": "FrontisAI/Frontis-MA1-30B-SFT",
		"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 "FrontisAI/Frontis-MA1-30B-SFT" \
        --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": "FrontisAI/Frontis-MA1-30B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FrontisAI/Frontis-MA1-30B-SFT with Docker Model Runner:
```
docker model run hf.co/FrontisAI/Frontis-MA1-30B-SFT
```

Frontis-MA1-30B-SFT

This is the supervised fine-tuning checkpoint of the Frontis-MA1 family, before OpenMLE reinforcement learning. It is intended for research on machine learning engineering and program transformation.

Field	Value
Base model	Qwen/Qwen3-30B-A3B-Thinking-2507
Training stage	Full-parameter supervised fine-tuning
Saved checkpoint	iteration 569 (zero-based boundary; configured 570 updates)
Training data	Dataset06 useful mixed top4, excluding RL460 task overlaps; 24,350 rows
Epochs / global batch	3 / 128
Learning rate	3e-5
Precision	BF16
Release location	FrontisAI/Frontis-MA1-30B-SFT, default revision `main`

The actual 24,350-row training input is distinct from the 26,259-example public SFT trace collection. Dataset cutoff configuration was 32,768 tokens; this does not establish validated long-context inference performance. No standalone SFT benchmark claim is made by this release. The separately released RL model is FrontisAI/Frontis-MA1-30B.

Loading

from transformers import AutoTokenizer, AutoModelForCausalLM

repo = "FrontisAI/Frontis-MA1-30B-SFT"
tokenizer = AutoTokenizer.from_pretrained(repo, revision="main")
model = AutoModelForCausalLM.from_pretrained(
    repo, revision="main", dtype="bfloat16", device_map="auto"
)

Pin the published commit SHA for reproducibility. This model requires substantial memory; use the dependency versions recorded in the release validation receipt.

Release boundary

This repository revision distributes inference weights and tokenizer/configuration assets. The original SFT save omitted optimizer and RNG state, so it is not a complete training-resume package. Conversion uses the archived SLIME source at commit 017e368a14ae94732396213f52c0803ca7883698, with the release-specific patch recorded in the manifest.

License and limitations

Original Frontis-MA1 material follows the existing repository's CC BY-NC 4.0 license. Preserve the upstream Apache 2.0 license and notices. Outputs may contain incorrect or unsafe code and require execution checks in an appropriate sandbox. Loading and generation smoke checks do not substitute for benchmark evaluation.

Downloads last month: -

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for FrontisAI/Frontis-MA1-30B-SFT

Base model

Qwen/Qwen3-30B-A3B-Thinking-2507

Finetuned

(45)

this model

Collection including FrontisAI/Frontis-MA1-30B-SFT

Frontis-MA1

Collection

8 items • Updated about 5 hours ago • 26