Instructions to use STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-sft with Transformers:

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

pipe = pipeline("text-generation", model="STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-sft")
model = AutoModelForCausalLM.from_pretrained("STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-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

vLLM

How to use STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-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": "STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-sft

SGLang

How to use STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-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 "STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-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": "STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-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 "STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-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": "STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-sft with Docker Model Runner:
```
docker model run hf.co/STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-sft
```

STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-sft

SFT-finetuned Qwen/Qwen3-4B-Instruct-2507 on the planner subset of Divij/qwen3-32b-mas-traces, which contains traces of Qwen3-32B acting as a planner agent in a multi-agent system. This model is the distilled student that learns to play the same role as Qwen3-32B in that pipeline.

Branches

Branch	Epochs trained	Notes
`main`	2	final

Training configuration

Base model: Qwen/Qwen3-4B-Instruct-2507
Dataset: Divij/qwen3-32b-mas-traces (config planner)
Loss: assistant-only (system + user tokens masked)
Optimizer: AdamW (β=(0.9, 0.95), wd=0.01, eps=1e-8)
Learning rate: 1e-5, constant with 3% warmup
Sequence length: 8192 (sequence packing on)
Precision: bf16
Hardware: 8× H100 80GB, DDP
Liger-Kernel: on (chunked CE + fused RMSNorm)

Inference

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "STEVENZHANG904/Qwen3-4B-Instruct-2507-planner-sft"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, dtype=torch.bfloat16, device_map="cuda")

# Planner role expects a task-spec prompt — see the dataset card for the exact format.
messages = [
    {"role": "system", "content": "You are a helpful, creative, and smart assistant."},
    {"role": "user", "content": "<your planner task spec here>"},
]
inputs = tok.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to("cuda")
out = model.generate(
    inputs, max_new_tokens=4096,
    do_sample=True, temperature=0.6, top_p=0.95,  # Qwen3 thinking-mode defaults
)
print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))

The model emits <think>...</think> reasoning blocks (inherited from Qwen3-32B traces). Use sampling, not greedy decoding — small distilled models can loop in <think> under greedy.