Instructions to use CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k with Transformers:

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

pipe = pipeline("text-generation", model="CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k")
model = AutoModelForCausalLM.from_pretrained("CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k")
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 CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k

SGLang

How to use CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k 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 "CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k" \
    --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": "CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k",
		"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 "CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k" \
        --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": "CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k 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 CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k 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 CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k",
    max_seq_length=2048,
)

Docker Model Runner
How to use CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k with Docker Model Runner:
```
docker model run hf.co/CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k
```

CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k

Fine-tuned from Qwen/Qwen3.6-27B on CyberNative text-only ShareGPT-style data.

Training settings:

Date: 20260529
Context: 32768 tokens
Base loading during training: 8-bit
LoRA: r=128, alpha=128, dropout=0.05
Epochs: 1
Learning rate: 0.0002
Warmup ratio: 0.05
Weight decay: 0.01
Effective batch size: 4
Train-on-assistant-only labels: True
Assistant reasoning: preserved from thinking / reasoning fields as <think>...</think> when present
MTP heads: not custom-trained; base MTP/speculative decoding capability preserved for serving.
Dataset: already processed combo.jsonl / CyberNative ShareGPT-style JSONL

Recommended serving note:

Enable Qwen MTP/speculative decoding in vLLM/SGLang at inference time if your serving stack supports it.

Downloads last month: 24

Safetensors

Model size

27B params

Tensor type

BF16

Model tree for CyberNative-AI/Qwen36_27B_CyberNative_20260529_8bitLoRA64_32k

Base model

Qwen/Qwen3.6-27B

Adapter

(129)

this model