Instructions to use CompiwerAI/Mtrini-SVL-2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CompiwerAI/Mtrini-SVL-2.0 with Transformers:

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

pipe = pipeline("image-text-to-text", model="CompiwerAI/Mtrini-SVL-2.0")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("CompiwerAI/Mtrini-SVL-2.0")
model = AutoModelForMultimodalLM.from_pretrained("CompiwerAI/Mtrini-SVL-2.0", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CompiwerAI/Mtrini-SVL-2.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CompiwerAI/Mtrini-SVL-2.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CompiwerAI/Mtrini-SVL-2.0",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/CompiwerAI/Mtrini-SVL-2.0

SGLang

How to use CompiwerAI/Mtrini-SVL-2.0 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 "CompiwerAI/Mtrini-SVL-2.0" \
    --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": "CompiwerAI/Mtrini-SVL-2.0",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "CompiwerAI/Mtrini-SVL-2.0" \
        --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": "CompiwerAI/Mtrini-SVL-2.0",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use CompiwerAI/Mtrini-SVL-2.0 with Docker Model Runner:
```
docker model run hf.co/CompiwerAI/Mtrini-SVL-2.0
```

Mtrini-SVL-2.0

File size: 1,656 Bytes

fe356f5

{"steps": 5, "max_steps": 5, "log": [{"loss": 0.6931473016738892, "grad_norm": 17.957149505615234, "learning_rate": 1.6666666666666667e-06, "entropy": 0.6042060684412718, "num_tokens": 129113.0, "logits/chosen": -2.031570067427444, "logits/rejected": -2.066084378741378, "mean_token_accuracy": 0.8573183789849281, "rewards/chosen": 0.0, "rewards/rejected": 0.0, "rewards/accuracies": 0.0, "rewards/margins": 0.0, "logps/chosen": -1720.7409473061562, "logps/rejected": -1911.8703248500824, "epoch": 0.43243243243243246, "step": 2}, {"loss": 0.7156742215156555, "grad_norm": 14.256765365600586, "learning_rate": 5e-06, "entropy": 0.7723287399858236, "num_tokens": 235146.0, "logits/chosen": -1.9302834164158855, "logits/rejected": -1.978542090787214, "mean_token_accuracy": 0.832091361284256, "rewards/chosen": -0.020962871101801284, "rewards/rejected": 0.020634264779801015, "rewards/accuracies": 0.4375, "rewards/margins": -0.04159713693661615, "logps/chosen": -1395.894810795784, "logps/rejected": -1786.6366989016533, "epoch": 0.8648648648648649, "step": 4}, {"train_runtime": 249.6526, "train_samples_per_second": 0.16, "train_steps_per_second": 0.02, "total_flos": 1.5657738870199104e+16, "train_loss": 0.7078817367553711, "entropy": 0.6014999866485595, "num_tokens": 277106.0, "logits/chosen": -2.0039181554060184, "logits/rejected": -1.9878743479109093, "mean_token_accuracy": 0.8745649218559265, "rewards/chosen": -0.044874840695410964, "rewards/rejected": -0.00777633311226964, "rewards/accuracies": 0.6, "rewards/margins": -0.03709850497543812, "logps/chosen": -1500.4318752288818, "logps/rejected": -1871.2910789489747, "epoch": 1.0, "step": 5}]}