---
library_name: transformers
license: apache-2.0
datasets:
- deepvk/LLaVA-Instruct-ru
- Lin-Chen/ShareGPT4V
- deepvk/GQA-ru
language:
- ru
- en
base_model: google/gemma-2b-it
pipeline_tag: image-text-to-text
---

# LLaVA-Gemma-2b-LORA

LLaVA-Gemma-2b-LORA is a Vision-Language Model (VLM) based on [`google/gemma-2b-it`](https://huggingface.co/google/gemma-2b-it) model
and trained in original LLaVA setup using LORA. This model is primarily adapted to work with Russian, but still capable to work with English.

## Usage

Model usage is simple via `transformers` API

```python
import requests

from PIL import Image
from transformers import AutoProcessor, AutoTokenizer, LlavaForConditionalGeneration

model_name = "deepvk/llava-gemma-2b-lora"

model = LlavaForConditionalGeneration.from_pretrained(model_name)
processor = AutoProcessor.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

url = "https://www.ilankelman.org/stopsigns/australia.jpg"
img = Image.open(requests.get(url, stream=True).raw)
messages = [
    {"role": "user", "content": "<image>\nОпиши картинку несколькими словами."}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(images=[img], text=text, return_tensors="pt")

generate_ids = model.generate(**inputs, max_new_tokens=30)
answer = tokenizer.decode(generate_ids[0, inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(answer)
```

Use the `<image>` tag to point to an image in the text and follow the chat template for a multi-turn conversation.
The model is capable of chatting without any images or working with multiple images in a conversation, but this behavior has not been tested.

The model format allows it to be directly used in popular frameworks,
e.g. you can test the model using [lmms-eval](https://github.com/EvolvingLMMs-Lab/lmms-eval), see Results section for details.


## Train

To train this model, we follow the original LLaVA pipeline and reuse [`haotian-liu/LLaVA`](https://github.com/haotian-liu/LLaVA) framework.

The model was trained in two stages:
1. The adapter was trained using pre-training data from [`ShareGPT4V`](https://github.com/InternLM/InternLM-XComposer/tree/main/projects/ShareGPT4V).
2. Instruction tuning included training the LLM and the adapter, for this we use:
    * [`deepvk/LLaVA-Instruct-ru`](https://huggingface.co/datasets/deepvk/LLaVA-Instruct-ru) — our new dataset of VLM instructions in Russian
    * [`deepvk/GQA-ru`](https://huggingface.co/datasets/deepvk/GQA-ru) — the training part of the popular GQA test, translated into Russian, we used the post-prompt "Ответь одним словом. ".
    * We also used instruction data from ShareGPT4V.

The entire training process took 3 days on a single A100 40GB.

## Results

The model's performance was evaluated using [`lmms-eval`](https://github.com/EvolvingLMMs-Lab/lmms-eval/tree/main) framework
```bash
accelerate launch -m lmms_eval --model llava_hf --model_args pretrained="deepvk/llava-gemma-2b-lora" \
  --tasks gqa-ru,mmbench_ru_dev,gqa,mmbench_en_dev --batch_size 1 \
  --log_samples --log_samples_suffix llava-saiga-8b --output_path ./logs/
```

| Model                                                                                           | GQA          | GQA-ru       | MMBench      | MMBench-ru   |
| ----------------------------------------------------------------------------------------------- |:------------:|:------------:|:------------:|:------------:|
| `deepvk/llava-gemma-2b-lora` [this model]                                                       | 56.39        | <u>46.37</u> | <u>51.72</u> | <u>40.19</u> |
| [`Intel/llava-gemma-2b`](https://huggingface.co/Intel/llava-gemma-2b)                           | <u>59.80</u> | 0.20         | 39.40        | 28.30        |
| [`deepvk/llava-saiga-8b`](https://huggingface.co/deepvk/llava-saiga-8b)                         | 62.00        | **51.44**    | 64.26        | **56.65**    |
| [`llava-hf/llava-1.5-7b-hf`](https://huggingface.co/llava-hf/llava-1.5-7b-hf)                   | 61.31        | 28.39        | 62.97        | 52.25        |
| [`llava-hf/llava-v1.6-mistral-7b-hf`](https://huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf) | **64.65**    | 6.65         | **67.70**    | 48.80        |

*Note*: for MMBench we didn't use OpenAI API for finding quantifier in generated string. Therefore, the score is similar to Exact Match as in GQA benchmark.

## Citation

```
@misc{liu2023llava,
  title={Visual Instruction Tuning}, 
  author={Liu, Haotian and Li, Chunyuan and Wu, Qingyang and Lee, Yong Jae},
  publisher={NeurIPS},
  year={2023},
}
```

```
@misc{deepvk2024llava-gemma-2b-lora,
	title={LLaVA-Gemma-2b-LORA},
	author={Belopolskih, Daniil and Spirin, Egor},
	url={https://huggingface.co/deepvk/llava-gemma-2b-lora},
	publisher={Hugging Face}
	year={2024},
}
```