Instructions to use nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615 with Transformers:

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

pipe = pipeline("text-generation", model="nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615")
model = AutoModelForCausalLM.from_pretrained("nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615", 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 nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615

SGLang

How to use nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615 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 "nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615" \
    --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": "nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615",
		"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 "nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615" \
        --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": "nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615",
    max_seq_length=2048,
)

Docker Model Runner
How to use nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615 with Docker Model Runner:
```
docker model run hf.co/nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615
```

qwen3-0-6b — Cybersecurity QA (SFT)

Fine-tuned on Kaggle using SFT.

Model Summary

Base: unsloth/Qwen3-0.6B
Trainable params: 187,044,352 / total 596,049,920
Train wall time (s): 33679.3
Files: pytorch_model.safetensors + config.json + tokenizer files

Data

Dataset: zobayer0x01/cybersecurity-qa
Samples: total=42427, train=38184, val=1500
Prompting: Chat template with a fixed system prompt:

You are a helpful assistant specialized in cybersecurity Q&A.

Training Config

Field	Value
Method	SFT
Precision	fp32
Quantization	none
Mode	steps
Num Epochs	1
Max Steps	4761
Eval Steps	1600
Save Steps	3200
LR	5e-05
Max Length	768
per_device_batch_size	1
grad_accum	8

Evaluation (greedy, fixed-length decode)

Metric	Score
BLEU-4	1.44
ROUGE-L	13.88
F1 (token-level)	25.88
chrF++	19.46
BERTScore F1	82.63
Perplexity	16.55

Notes: We normalize whitespace/punctuations, compute token-level P/R/F1, and use evaluate's sacrebleu/rouge/chrf/bertscore.

How to use

from transformers import AutoTokenizer, AutoModelForCausalLM
tok = AutoTokenizer.from_pretrained("nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615")
mdl = AutoModelForCausalLM.from_pretrained("nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615")
prompt = tok.apply_chat_template(
    [{"role":"system","content":"You are a helpful assistant specialized in cybersecurity Q&A."},
     {"role":"user","content":"Explain SQL injection in one paragraph."}],
    tokenize=False, add_generation_prompt=True
)
ids = tok(prompt, return_tensors="pt").input_ids
out = mdl.generate(ids, max_new_tokens=128, do_sample=False)
print(tok.decode(out[0][ids.shape[-1]:], skip_special_tokens=True))

Intended Use & Limitations

Domain: cybersecurity Q&A; not guaranteed to be accurate for legal/medical purposes.
The model can hallucinate or produce outdated guidance—verify before applying in production.
Safety: No explicit content filtering. Add guardrails (moderation, retrieval augmentation) for deployment.

Reproducibility (env)

transformers>=4.43,<5, accelerate>=0.33,<0.34, peft>=0.11,<0.13, datasets>=2.18,<3, evaluate>=0.4,<0.5, rouge-score, sacrebleu, huggingface_hub>=0.23,<0.26, bitsandbytes
GPU: T4-class; LoRA recommended for low VRAM.

Changelog

2025-11-24 16:16 — Initial release (SFT)

Downloads last month: 7

Safetensors

Model size

0.6B params

Tensor type

F32

Model tree for nhonhoccode/qwen3-0-6b-cybersecqa-sft-freeze2-20251124-1615

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

unsloth/Qwen3-0.6B

Finetuned

(287)

this model