Instructions to use lablab-ai-amd-developer-hackathon/CyberSecQwen-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lablab-ai-amd-developer-hackathon/CyberSecQwen-4B with Transformers:

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

pipe = pipeline("text-generation", model="lablab-ai-amd-developer-hackathon/CyberSecQwen-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lablab-ai-amd-developer-hackathon/CyberSecQwen-4B")
model = AutoModelForCausalLM.from_pretrained("lablab-ai-amd-developer-hackathon/CyberSecQwen-4B")
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]:]))

PEFT
How to use lablab-ai-amd-developer-hackathon/CyberSecQwen-4B with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use lablab-ai-amd-developer-hackathon/CyberSecQwen-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lablab-ai-amd-developer-hackathon/CyberSecQwen-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lablab-ai-amd-developer-hackathon/CyberSecQwen-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lablab-ai-amd-developer-hackathon/CyberSecQwen-4B

SGLang

How to use lablab-ai-amd-developer-hackathon/CyberSecQwen-4B 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 "lablab-ai-amd-developer-hackathon/CyberSecQwen-4B" \
    --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": "lablab-ai-amd-developer-hackathon/CyberSecQwen-4B",
		"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 "lablab-ai-amd-developer-hackathon/CyberSecQwen-4B" \
        --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": "lablab-ai-amd-developer-hackathon/CyberSecQwen-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lablab-ai-amd-developer-hackathon/CyberSecQwen-4B with Docker Model Runner:
```
docker model run hf.co/lablab-ai-amd-developer-hackathon/CyberSecQwen-4B
```

athena129 commited on 13 days ago

Commit

c300739

verified ·

1 Parent(s): aa0deee

Drop NVIDIA SKU mentions, keep technical portability claim

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -111,7 +111,7 @@ The numbers below are first-principles estimates from the bf16 weight footprint
 | bf16 weight file on disk | ~8.0 GB | ~16 GB |
 | Inference VRAM, weights only (bf16) | ~8 GB | ~16 GB |
 | Inference VRAM, weights + 4 K KV cache (bf16) | ~9–10 GB | ~17–18 GB |
-| Single-GPU class (bf16, headroom for batch ≥ 1) | Fits on 12 GB+ consumer GPU (e.g., RTX 3060 12 GB, RTX 4070 12 GB, T4 16 GB) | Typically requires 24 GB+ (e.g., RTX 4090, A10, A100 40 GB) |
 | AMD Instinct MI300X 192 GB (validated) | Fits trivially with very large batch / long context | Fits trivially |
 Notes:

 | bf16 weight file on disk | ~8.0 GB | ~16 GB |
 | Inference VRAM, weights only (bf16) | ~8 GB | ~16 GB |
 | Inference VRAM, weights + 4 K KV cache (bf16) | ~9–10 GB | ~17–18 GB |
+| Single-GPU class (bf16, headroom for batch ≥ 1) | Fits on any 12 GB+ consumer card | Typically requires a 24 GB+ datacenter card |
 | AMD Instinct MI300X 192 GB (validated) | Fits trivially with very large batch / long context | Fits trivially |
 Notes: