README.md

metadata

base_model:
  - mistralai/Mistral-7B-Instruct-v0.2
library_name: transformers
license: mit
pipeline_tag: video-text-to-text

VideoChat2-TPO

This model is based on the paper Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment.

🏃 Installation

pip install -r requirements.txt
python app.py

🔧 Usage

from transformers import AutoModel, AutoTokenizer
from tokenizer import MultimodalLlamaTokenizer

model_path = "OpenGVLab/VideoChat-TPO"
tokenizer =  AutoTokenizer.from_pretrained(model_path,
trust_remote_code=True,
use_fast=False,)
model = AutoModel.from_pretrained(model_path,  trust_remote_code=True, _tokenizer=self.tokenizer).eval()