metadata

inference: false
language:
  - en
tags:
  - 'LLaMA '
  - MultiModal

This is a Hugging Face friendly Model, the original can be found at https://huggingface.co/liuhaotian/llava-llama-2-7b-chat-lightning-lora-preview

LLaVA Model Card

Model details

Model type: LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture.

Model date: LLaVA-LLaMA-2-7B-Chat-LoRA-Preview was trained in July 2023.

Paper or resources for more information: https://llava-vl.github.io/

License

Where to send questions or comments about the model: https://github.com/haotian-liu/LLaVA/issues

Intended use

Primary intended uses: The primary use of LLaVA is research on large multimodal models and chatbots.

Primary intended users: The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.

Training dataset

558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.
80K GPT-generated multimodal instruction-following data.

Evaluation dataset

A preliminary evaluation of the model quality is conducted by creating a set of 90 visual reasoning questions from 30 unique images randomly sampled from COCO val 2014 and each is associated with three types of questions: conversational, detailed description, and complex reasoning. We utilize GPT-4 to judge the model outputs. We also evaluate our model on the ScienceQA dataset. Our synergy with GPT-4 sets a new state-of-the-art on the dataset. See https://llava-vl.github.io/ for more details.

Usage

usage is as follows

from transformers import LlavaProcessor, LlavaForCausalLM
from PIL import Image
import requests
import torch

PATH_TO_CONVERTED_WEIGHTS = "shauray/Llava-Llama-2-7B-hf"

model = LlavaForCausalLM.from_pretrained(PATH_TO_CONVERTED_WEIGHTS,
device_map="cuda",torch_dtype=torch.float16).to("cuda")
processor = LlavaProcessor.from_pretrained(PATH_TO_CONVERTED_WEIGHTS)

url = "https://llava-vl.github.io/static/images/view.jpg"
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")
prompt = "How can you best describe this image?"

inputs = processor(text=prompt, images=image, return_tensors="pt").to("cuda",
torch.float16)
# Generate
generate_ids = model.generate(**inputs, 
    do_sample=True,
    max_length=1024,
    temperature=0.1,
    top_p=0.9,
)
out = processor.decode(generate_ids[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True).strip()

print(out)

"""The photograph shows a wooden dock floating on the water, with mountains in the background. It is an idyllic scene that captures both
nature and human-made structures at their finest moments of beauty or tranquility depending upon one's perspective as they gaze into it"""