Instructions to use Pongsasit/nemotron-3-sfted with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pongsasit/nemotron-3-sfted with Transformers:

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

pipe = pipeline("text-generation", model="Pongsasit/nemotron-3-sfted", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Pongsasit/nemotron-3-sfted", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Pongsasit/nemotron-3-sfted", trust_remote_code=True)
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 Pongsasit/nemotron-3-sfted with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pongsasit/nemotron-3-sfted"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pongsasit/nemotron-3-sfted",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pongsasit/nemotron-3-sfted

SGLang

How to use Pongsasit/nemotron-3-sfted 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 "Pongsasit/nemotron-3-sfted" \
    --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": "Pongsasit/nemotron-3-sfted",
		"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 "Pongsasit/nemotron-3-sfted" \
        --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": "Pongsasit/nemotron-3-sfted",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Pongsasit/nemotron-3-sfted with Docker Model Runner:
```
docker model run hf.co/Pongsasit/nemotron-3-sfted
```

nemotron-3-sfted

Supervised fine-tune (full SFT) of nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 on the nvidia/Nemotron-SFT-Safety-v2 dataset, aimed at improving safe-response behavior while preserving the base model's reasoning ability.

Model details

Base model: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 (30B total / ~3B active, MoE + Mamba hybrid)
Fine-tuning method: Full supervised fine-tuning (all parameters)
Dataset: nvidia/Nemotron-SFT-Safety-v2 (English subset)
Precision: BF16
Framework: Megatron-Bridge

Training configuration

Setting	Value
Parallelism	Tensor (TP) = 1, Expert (EP) = 8
Optimizer	Adam (fp32 states, CPU offload enabled)
Hardware	8x GPU node
Reasoning format	`<think> ... </think>` traces preserved from the dataset
The dataset was preprocessed into chat-templated `input`/`output` pairs using the
base model's tokenizer, with reasoning content wrapped in `<think>...</think>`
ahead of the final response.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "Pongsasit/nemotron-3-sfted"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id, trust_remote_code=True, torch_dtype="bfloat16", device_map="auto"
)
messages = [{"role": "user", "content": "How do I keep my online accounts secure?"}]
inputs = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, return_tensors="pt"
).to(model.device)
outputs = model.generate(inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 23

Safetensors

Model size

32B params

Tensor type

F32

BF16

Model tree for Pongsasit/nemotron-3-sfted

Base model

nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Finetuned

(53)

this model

Pongsasit
/

nemotron-3-sfted

nemotron-3-sfted

Model details

Training configuration

Usage

Model tree for Pongsasit/nemotron-3-sfted

Dataset used to train Pongsasit/nemotron-3-sfted