Instructions to use Legad/qwen25-vl-scangas with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Legad/qwen25-vl-scangas with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "Legad/qwen25-vl-scangas")

Transformers

How to use Legad/qwen25-vl-scangas with Transformers:

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

pipe = pipeline("text-generation", model="Legad/qwen25-vl-scangas")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Legad/qwen25-vl-scangas")
model = AutoModelForMultimodalLM.from_pretrained("Legad/qwen25-vl-scangas", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Legad/qwen25-vl-scangas with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Legad/qwen25-vl-scangas"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Legad/qwen25-vl-scangas",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Legad/qwen25-vl-scangas

SGLang

How to use Legad/qwen25-vl-scangas 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 "Legad/qwen25-vl-scangas" \
    --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": "Legad/qwen25-vl-scangas",
		"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 "Legad/qwen25-vl-scangas" \
        --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": "Legad/qwen25-vl-scangas",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Legad/qwen25-vl-scangas with Docker Model Runner:
```
docker model run hf.co/Legad/qwen25-vl-scangas
```

See axolotl config

axolotl version: 0.13.0.dev0

base_model: Qwen/Qwen2.5-VL-7B-Instruct

processor_type: AutoProcessor
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
bf16: true
fp16: false

adapter: lora
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - k_proj
  - v_proj
  - o_proj
  - gate_proj
  - up_proj
  - down_proj

datasets:
  - path: Legad/scangas-images
    type: chat_template
    field_messages: messages
    field_images: images

remove_unused_columns: false
skip_prepare_dataset: true
sample_packing: false

sequence_len: 2048
micro_batch_size: 1
gradient_checkpointing: true
gradient_accumulation_steps: 4
num_epochs: 10
learning_rate: 2e-4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine

output_dir: ./outputs/qwen25-vl-finetuned
save_safetensors: true

outputs/qwen25-vl-finetuned

This model is a fine-tuned version of Qwen/Qwen2.5-VL-7B-Instruct on the Legad/scangas-images dataset.

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: 0.0002
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 5
training_steps: 188

Training results

Framework versions

PEFT 0.17.1
Transformers 4.57.0
Pytorch 2.7.1+cu126
Datasets 4.0.0
Tokenizers 0.22.1

Downloads last month: 1

Model tree for Legad/qwen25-vl-scangas

Base model

Qwen/Qwen2.5-VL-7B-Instruct

Adapter

(329)

this model

Legad
/

qwen25-vl-scangas

outputs/qwen25-vl-finetuned

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for Legad/qwen25-vl-scangas

Dataset used to train Legad/qwen25-vl-scangas