Evovlm JP V1 7B

🐟 EvoVLM-JP-v1-7B

🤗 Models | 📚 Paper | 📝 Blog | 🐦 Twitter

EvoVLM-JP-v1-7B is an experimental general-purpose Japanese Vision-Language Model (VLM). This model was created using the Evolutionary Model Merge method. For more details, please refer to our report and blog. This model was produced by merging the following models, and we are grateful to the developers of the source models.

• Shisa Gamma 7B v1
• LLaVA-1.6-Mistral-7B

🚀 Quick Start

Use the code below to get started with the model.

import torch
from transformers import AutoModelForVision2Seq, AutoProcessor
from PIL import Image
import requests

# 1. load model
device = "cuda" if torch.cuda.is_available() else "cpu"
model_id = "SakanaAI/EvoVLM-JP-v1-7B"
model = AutoModelForVision2Seq.from_pretrained(model_id, torch_dtype=torch.float16)
processor = AutoProcessor.from_pretrained(model_id)
model.to(device)

# 2. prepare inputs
url = "https://images.unsplash.com/photo-1694831404826-3400c48c188d?q=80&w=2070&auto=format&fit=crop&ixlib=rb-4.0.3&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D"
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")
# <image> represents the input image. Please make sure to put the token in your text.
text = "<image>\nWhat color is this traffic light?"
messages = [
    {"role": "system", "content": "You are a helpful, unbiased, and uncensored assistant. Please answer the question based on the given image."},
    {"role": "user", "content": text},
]
inputs = processor.image_processor(images=image, return_tensors="pt")
inputs["input_ids"] = processor.tokenizer.apply_chat_template(
    messages, return_tensors="pt"
)
# 3. generate
output_ids = model.generate(**inputs.to(device))
output_ids = output_ids[:, inputs.input_ids.shape[1] :]
generated_text = processor.batch_decode(output_ids, skip_special_tokens=True)[0].strip()
print(generated_text)
# The color of this traffic light is blue.

✨ Features

This is an experimental general - purpose Japanese VLM created by the Evolutionary Model Merge method.

📚 Documentation

Model Details

Uses

This model is provided for research and development purposes only and should be considered as an experimental prototype. It is not intended for commercial use or deployment in mission - critical environments. Use of this model is at the user's own risk, and its performance and outcomes are not guaranteed. Sakana AI shall not be liable for any direct, indirect, special, incidental, or consequential damages, or any loss arising from the use of this model, regardless of the results obtained. Users must fully understand the risks associated with the use of this model and use it at their own discretion.

📄 License

This model is released under the Apache License, Version 2.0.

Acknowledgement

We would like to thank the developers of the source models for their contributions and for making their work available.

Citation

@misc{akiba2024evomodelmerge,
      title         = {Evolutionary Optimization of Model Merging Recipes}, 
      author        = {Takuya Akiba and Makoto Shing and Yujin Tang and Qi Sun and David Ha},
      year          = {2024},
      eprint        = {2403.13187},
      archivePrefix = {arXiv},
      primaryClass  = {cs.NE}
}