Instructions to use Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental with Transformers:

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

pipe = pipeline("image-text-to-text", model="Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental")
model = AutoModelForImageTextToText.from_pretrained("Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental")
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

vLLM

How to use Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental",
		"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/Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental

SGLang

How to use Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental 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 "Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental" \
    --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": "Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental",
		"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 "Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental" \
        --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": "Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental",
		"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 Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental with Docker Model Runner:
```
docker model run hf.co/Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

💨👁️ Vikhr-2-VL-2b-Instruct-experimental

Vikhr-2-VL-2b-Instruct-experimental — это компактная VLM модель на базе Qwen2-VL-2B-Instruct, обученная на переведенном датасете LLAVA-150K, специально доученная для обработки на русском языке. Дообученная модель является эксперементальной и не всегда будет работать ожидаемо (особенно OCR). Для обратной связи используйте Vikhr Models

Попробовать / Try now:

Авторы / Authors

Nikolay Kompanets, LakoMoor, Vikhr Team
Sergey Bratchikov, NlpWonder, Vikhr Team
Konstantin Korolev, underground, Vikhr Team
Aleksandr Nikolich, Vikhr Team

@inproceedings{nikolich2024vikhr,
  title={Vikhr: Constructing a State-of-the-art Bilingual Open-Source Instruction-Following Large Language Model for {Russian}},
  author={Aleksandr Nikolich and Konstantin Korolev and Sergei Bratchikov and Nikolay Kompanets and Igor Kiselev and Artem Shelmanov },
  booktitle = {Proceedings of the 4rd Workshop on Multilingual Representation Learning (MRL) @ EMNLP-2024}
  year={2024},
  publisher = {Association for Computational Linguistics},
  url={https://arxiv.org/pdf/2405.13929}
}