Instructions to use BodyCam-VQA/qwen3-30b-sft-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BodyCam-VQA/qwen3-30b-sft-qa with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-30B-A3B-Thinking-2507")
model = PeftModel.from_pretrained(base_model, "BodyCam-VQA/qwen3-30b-sft-qa")

Transformers

How to use BodyCam-VQA/qwen3-30b-sft-qa with Transformers:

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

pipe = pipeline("text-generation", model="BodyCam-VQA/qwen3-30b-sft-qa")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("BodyCam-VQA/qwen3-30b-sft-qa", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BodyCam-VQA/qwen3-30b-sft-qa with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BodyCam-VQA/qwen3-30b-sft-qa"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BodyCam-VQA/qwen3-30b-sft-qa",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BodyCam-VQA/qwen3-30b-sft-qa

SGLang

How to use BodyCam-VQA/qwen3-30b-sft-qa 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 "BodyCam-VQA/qwen3-30b-sft-qa" \
    --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": "BodyCam-VQA/qwen3-30b-sft-qa",
		"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 "BodyCam-VQA/qwen3-30b-sft-qa" \
        --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": "BodyCam-VQA/qwen3-30b-sft-qa",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BodyCam-VQA/qwen3-30b-sft-qa with Docker Model Runner:
```
docker model run hf.co/BodyCam-VQA/qwen3-30b-sft-qa
```

Model Card for Model ID

Pre-trained adapters for question generation on police body-worn camera footage, designed to work with Qwen/Qwen3-30B-A3B-Thinking-2507. Trained using standard fine-tuning (SFT).

Usage

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.float16,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
)

model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen3-30B-A3B-Thinking-2507",
    quantization_config=bnb_config,
    device_map="auto",
)

self.model = PeftModel.from_pretrained(model, "ADAPTER/PATH", torch_dtype=torch.float16)

Architecture

Base Model: Qwen3-30B-A3B-Thinking-2507

Training

Trained on high quality investigative questions and the corresponding chain of thought (CoT) tokens generated by Deepseek V3.2 (Reasoner)

Github Repository

Full Codebase: https://github.com/Karish-Gupta/BodyCam-VQA/tree/main/fine_tuning

Framework versions

PEFT 0.18.1

Downloads last month: 1

Model tree for BodyCam-VQA/qwen3-30b-sft-qa

Base model

Qwen/Qwen3-30B-A3B-Thinking-2507

Adapter

(9)

this model