Heron Chat Git Ja Stablelm Base 7b V1

🚀 Heron GIT Japanese StableLM Base 7B

A vision - language model that can converse about input images, offering capabilities in chat - like applications and research.

🚀 Quick Start

Follow the installation guide.

💻 Usage Examples

Basic Usage

import torch
from heron.models.git_llm.git_japanese_stablelm_alpha import GitJapaneseStableLMAlphaForCausalLM
from transformers import AutoProcessor, LlamaTokenizer

device_id = 0
device = f"cuda:{device_id}"

MODEL_NAME = "turing-motors/heron-chat-git-ja-stablelm-base-7b-v1"
    
model = GitJapaneseStableLMAlphaForCausalLM.from_pretrained(
    MODEL_NAME, torch_dtype=torch.float16, ignore_mismatched_sizes=True
)
model.eval()
model.to(device)

# prepare a processor
processor = AutoProcessor.from_pretrained(MODEL_NAME)
tokenizer = LlamaTokenizer.from_pretrained(
    "novelai/nerdstash-tokenizer-v1",
    padding_side="right",
    additional_special_tokens=["▁▁"],
)
processor.tokenizer = tokenizer


import requests
from PIL import Image

# 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"##human: この画像の面白い点は何ですか?\n##gpt: "

# do preprocessing
inputs = processor(
    text=text,
    images=image,
    return_tensors="pt",
    truncation=True,
)

inputs = {k: v.to(device) for k, v in inputs.items()}

# do inference
with torch.no_grad():
    out = model.generate(**inputs, max_length=256, do_sample=False, temperature=0., no_repeat_ngram_size=2)

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

📚 Documentation

Model Details

Heron GIT Japanese StableLM Base 7B is a vision - language model that can converse about input images. This model was trained using the heron library. Please refer to the code for details.

Training

1. The GIT adaptor was trained with LLaVA - Pratrain - JA.
2. The LLM and the adapter were fully fine - tuned with LLaVA - Instruct - 620K - JA - v2.

Training Dataset

1. LLaVA - Pratrain - JA
2. LLaVA - Instruct - 620K - JA - v2

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.

📄 License

This project is licensed under the CC BY - NC 4.0 license.

📚 How to cite

@misc{inoue2024heronbench,
      title={Heron-Bench: A Benchmark for Evaluating Vision Language Models in Japanese}, 
      author={Yuichi Inoue and Kento Sasaki and Yuma Ochi and Kazuki Fujii and Kotaro Tanahashi and Yu Yamaguchi},
      year={2024},
      eprint={2404.07824},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}