Instructions to use HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA with Transformers:

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

pipe = pipeline("text-generation", model="HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA")
model = AutoModelForCausalLM.from_pretrained("HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA

SGLang

How to use HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA 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 "HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA" \
    --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": "HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA",
		"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 "HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA" \
        --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": "HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA with Docker Model Runner:
```
docker model run hf.co/HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA
```

Model Card for Qwen3-0.6B-Fable5-Reasoning

This model is a fine-tuned version of Qwen/Qwen3-0.6B.

It was trained using Supervised Fine-Tuning (SFT) with TRL. The LoRA weights were merged with the base model, resulting in a standalone model that can be loaded directly with Transformers.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"

generator = pipeline(
    "text-generation",
    model="HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA",
    device="cuda"
)

output = generator(
    [{"role": "user", "content": question}],
    max_new_tokens=128,
    return_full_text=False
)[0]

print(output["generated_text"])

Training procedure

This model was fine-tuned from Qwen/Qwen3-0.6B using Supervised Fine-Tuning (SFT).

Parameter-efficient fine-tuning was performed using LoRA, and the resulting adapter weights were merged with the base model. The uploaded repository therefore contains a standalone merged model rather than a separate adapter.

Framework versions

TRL: 1.10.0
Transformers: 5.15.0
PyTorch: 2.13.0+cu132
Datasets: 5.0.1
Tokenizers: 0.22.2

Citation

If you use this model in your research or project, please cite:

@misc{hellsingemperor2026qwen3fable5,
  author = {HellsingEmperor},
  title = {Qwen3-0.6B-Fable5-Reasoning},
  year = {2026},
  publisher = {Hugging Face},
  url = {https://huggingface.co/HellsingEmperor/Qwen3-0.6B-Fable5-Reasoning-LoRA}
}

Citations

Cite TRL as:

@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and GallouÃ©dec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}