---
language:
- ja
tags:
- heron
- vision
- image-captioning
- VQA
pipeline_tag: image-to-text
license:
- apache-2.0
inference: false
---
# Heron BLIP Japanese StableLM Base 7B

![heron](./heron_image.png)

## Model Details
Heron BLIP Japanese StableLM Base 7B is a vision-language model that can converse about input images.<br>
This model was trained using [the heron library](https://github.com/turingmotors/heron). Please refer to the code for details.


## Usage

Follow [the installation guide](https://github.com/turingmotors/heron/tree/dev-0.0.1#1-clone-this-repository). 

```python
import requests
from PIL import Image

import torch
from transformers import AutoProcessor
from heron.models.git_llm.git_llama import GitLlamaForCausalLM

device_id = 0

# prepare a pretrained model
model = GitLlamaForCausalLM.from_pretrained('turing-motors/heron-chat-git-ja-stablelm-base-7b-v0')
model.eval()
model.to(f"cuda:{device_id}")

# prepare a processor
processor = AutoProcessor.from_pretrained('turing-motors/heron-chat-git-ja-stablelm-base-7b-v0', additional_special_tokens=["▁▁"])

# prepare inputs
url = "https://www.barnorama.com/wp-content/uploads/2016/12/03-Confusing-Pictures.jpg"
image = Image.open(requests.get(url, stream=True).raw)

text = f"##Instruction: Please answer the following question concletely. ##Question: What is unusual about this image? Explain precisely and concletely what he is doing? ##Answer: "

# do preprocessing
inputs = processor(
    text,
    image,
    return_tensors="pt",
    truncation=True,
)
inputs = {k: v.to(f"cuda:{device_id}") for k, v in inputs.items()}

# set eos token
eos_token_id_list = [
    processor.tokenizer.pad_token_id,
    processor.tokenizer.eos_token_id,
]

# do inference
with torch.no_grad():
    out = model.generate(**inputs, max_length=256, do_sample=False, temperature=0., eos_token_id=eos_token_id_list)

# print result
print(processor.tokenizer.batch_decode(out))
```


## Model Details
* **Developed by**: [Turing Inc.](https://www.turing-motors.com/)
* **Adaptor type**: [BLIP2](https://arxiv.org/abs/2301.12597)
* **Lamguage Model**: [Japanese StableLM Base Alpha](https://huggingface.co/stabilityai/japanese-stablelm-base-alpha-7b)
* **Language(s)**: Japanese
* **License**: This model is licensed under [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0).

### Training
This model was initially trained with the Adaptor using STAIR Captions. In the second phase, it was fine-tuned with [LLaVA-Instruct-150K-JA](https://huggingface.co/datasets/turing-motors/LLaVA-Instruct-150K-JA) and Japanese Visual Genome using LoRA.

### Training Dataset

- [LLaVA-Instruct-150K-JA](https://huggingface.co/datasets/turing-motors/LLaVA-Instruct-150K-JA)
- [Japanese STAIR Captions](http://captions.stair.center/)
- [Japanese Visual Genome VQA dataset](https://github.com/yahoojapan/ja-vg-vqa)

## Use and Limitations

### Intended Use

This model is intended for use in chat-like applications and for research purposes.

### Limitations

The model may produce inaccurate or false information, and its accuracy is not guaranteed. It is still in the research and development stage.

## How to cite
```bibtex
@misc{GitJapaneseStableLM, 
    url    = {[https://huggingface.co/turing-motors/heron-chat-blip-ja-stablelm-base-7b-v0](https://huggingface.co/turing-motors/heron-chat-blip-ja-stablelm-base-7b-v0)}, 
    title  = {Heron BLIP Japanese StableLM Base 7B}, 
    author = {Kotaro Tanahashi, Yuichi Inoue, and Yu Yamaguchi}
}
```

## Citations

```bibtex
@misc{JapaneseInstructBLIPAlpha, 
    url    = {[https://huggingface.co/stabilityai/japanese-instructblip-alpha](https://huggingface.co/stabilityai/japanese-instructblip-alpha)}, 
    title  = {Japanese InstructBLIP Alpha}, 
    author = {Shing, Makoto and Akiba, Takuya}
}
```

---
license: apache-2.0
---