Instructions to use natolambert/qwen3-dgx-spark-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use natolambert/qwen3-dgx-spark-sft with Transformers:

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

pipe = pipeline("text-generation", model="natolambert/qwen3-dgx-spark-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("natolambert/qwen3-dgx-spark-sft")
model = AutoModelForCausalLM.from_pretrained("natolambert/qwen3-dgx-spark-sft")
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 natolambert/qwen3-dgx-spark-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "natolambert/qwen3-dgx-spark-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": "natolambert/qwen3-dgx-spark-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/natolambert/qwen3-dgx-spark-sft

SGLang

How to use natolambert/qwen3-dgx-spark-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 "natolambert/qwen3-dgx-spark-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": "natolambert/qwen3-dgx-spark-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 "natolambert/qwen3-dgx-spark-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": "natolambert/qwen3-dgx-spark-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use natolambert/qwen3-dgx-spark-sft with Docker Model Runner:
```
docker model run hf.co/natolambert/qwen3-dgx-spark-sft
```

Qwen3 0.6B SFT (DGX Spark)

A supervised fine-tuned version of Qwen3-0.6B trained on the no_robots dataset.

Training Details

This model was trained on an NVIDIA DGX Spark (GB10 Blackwell GPU) as part of testing open-instruct on the new hardware platform.

Parameter	Value
Base model	Qwen/Qwen3-0.6B
Dataset	HuggingFaceH4/no_robots
Epochs	2
Batch size	32
Gradient accumulation	4
Learning rate	2e-5
Scheduler	cosine
Max sequence length	1024
Precision	bf16

Hardware

GPU: NVIDIA GB10 (Blackwell, sm_121)
Memory: 128GB unified CPU/GPU
CUDA: 13.0

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("natolambert/qwen3-dgx-spark-sft")
tokenizer = AutoTokenizer.from_pretrained("natolambert/qwen3-dgx-spark-sft")

messages = [{"role": "user", "content": "Write a short poem about machine learning."}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training Script

Trained using the DGX Spark SFT script from open-instruct:

./scripts/train/dgx-spark/sft_no_robots.sh

See dgx-spark-setup for details on running ML training on DGX Spark.

Limitations

This is primarily a test model to validate the DGX Spark training pipeline. It has not been extensively evaluated for downstream tasks.

Downloads last month: 9

Model tree for natolambert/qwen3-dgx-spark-sft

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

(970)

this model

natolambert
/

qwen3-dgx-spark-sft