Instructions to use Luxinos/sb-v3-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Luxinos/sb-v3-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-VL-32B-Instruct")
model = PeftModel.from_pretrained(base_model, "Luxinos/sb-v3-lora")

Transformers

How to use Luxinos/sb-v3-lora with Transformers:

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

pipe = pipeline("text-generation", model="Luxinos/sb-v3-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Luxinos/sb-v3-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Luxinos/sb-v3-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Luxinos/sb-v3-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": "Luxinos/sb-v3-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Luxinos/sb-v3-lora

SGLang

How to use Luxinos/sb-v3-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 "Luxinos/sb-v3-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": "Luxinos/sb-v3-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 "Luxinos/sb-v3-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": "Luxinos/sb-v3-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Luxinos/sb-v3-lora with Docker Model Runner:
```
docker model run hf.co/Luxinos/sb-v3-lora
```

survey_bot_lora

This model is a fine-tuned version of Qwen/Qwen3-VL-32B-Instruct on the survey_botv2 dataset. It achieves the following results on the evaluation set:

Loss: 0.3348

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 16
total_train_batch_size: 32
total_eval_batch_size: 2
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.4381	0.7508	100	0.4065
0.3366	1.4955	200	0.3543
0.2415	2.2403	300	0.3381
0.2678	2.9911	400	0.3347

Framework versions

PEFT 0.17.1
Transformers 4.57.1
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

Downloads last month: -

Model tree for Luxinos/sb-v3-lora

Base model

Qwen/Qwen3-VL-32B-Instruct

Adapter

(9)

this model