Instructions to use AIPlans/Qwen3-0.6B-SFT-hs2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AIPlans/Qwen3-0.6B-SFT-hs2 with Transformers:

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

pipe = pipeline("text-generation", model="AIPlans/Qwen3-0.6B-SFT-hs2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AIPlans/Qwen3-0.6B-SFT-hs2")
model = AutoModelForCausalLM.from_pretrained("AIPlans/Qwen3-0.6B-SFT-hs2", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AIPlans/Qwen3-0.6B-SFT-hs2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AIPlans/Qwen3-0.6B-SFT-hs2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AIPlans/Qwen3-0.6B-SFT-hs2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AIPlans/Qwen3-0.6B-SFT-hs2

SGLang

How to use AIPlans/Qwen3-0.6B-SFT-hs2 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 "AIPlans/Qwen3-0.6B-SFT-hs2" \
    --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": "AIPlans/Qwen3-0.6B-SFT-hs2",
		"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 "AIPlans/Qwen3-0.6B-SFT-hs2" \
        --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": "AIPlans/Qwen3-0.6B-SFT-hs2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AIPlans/Qwen3-0.6B-SFT-hs2 with Docker Model Runner:
```
docker model run hf.co/AIPlans/Qwen3-0.6B-SFT-hs2
```

Model Card for qwen3-0.6b-SFT-hs2

This model is a fine-tuned version of Qwen/Qwen3-0.6B-Base. It has been trained using TRL. Intended Use: Research on model diffing, preference fine-tuning, and evaluation of lightweight LLM behavior changes. It was developed for use in the Model Diffing project of AI-Plans.

Training procedure

This model is a SFT model and was trained with the chosen responses only(with score >=3), of the dataset used. It took about 1hr 10 mins for training with an A100(40 GB).

Framework versions

TRL: 0.25.1
Transformers: 4.57.3
Pytorch: 2.9.0+cu126
Datasets: 4.4.1
Tokenizers: 0.22.1

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}

Downloads last month: 16

Safetensors

Model size

0.6B params

Tensor type

F32

Model tree for AIPlans/Qwen3-0.6B-SFT-hs2

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

(660)

this model

AIPlans
/

Qwen3-0.6B-SFT-hs2

Model Card for qwen3-0.6b-SFT-hs2

Training procedure

Framework versions

Citations

Model tree for AIPlans/Qwen3-0.6B-SFT-hs2

Datasets used to train AIPlans/Qwen3-0.6B-SFT-hs2