cogvlm-base-490-hf

import torch
import requests
from PIL import Image
from transformers import AutoModelForCausalLM, LlamaTokenizer

tokenizer = LlamaTokenizer.from_pretrained('lmsys/vicuna-7b-v1.5')
model = AutoModelForCausalLM.from_pretrained(
    'THUDM/cogvlm-base-490-hf',
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    trust_remote_code=True
).to('cuda').eval()

image = Image.open(requests.get('https://github.com/THUDM/CogVLM/blob/main/examples/1.png?raw=true', stream=True).raw).convert('RGB')
inputs = model.build_conversation_input_ids(tokenizer, query='', images=[image])
inputs = {
    'input_ids': inputs['input_ids'].unsqueeze(0).to('cuda'),
    'token_type_ids': inputs['token_type_ids'].unsqueeze(0).to('cuda'),
    'attention_mask': inputs['attention_mask'].unsqueeze(0).to('cuda'),
    'images': [[inputs['images'][0].to('cuda').to(torch.bfloat16)]],
}
gen_kwargs = {"max_length": 2048, "do_sample": False}

with torch.no_grad():
    outputs = model.generate(**inputs, **gen_kwargs)
    outputs = outputs[:, inputs['input_ids'].shape[1]:]
    print(tokenizer.decode(outputs[0]))

@article{wang2023cogvlm,
      title={CogVLM: Visual Expert for Pretrained Language Models}, 
      author={Weihan Wang and Qingsong Lv and Wenmeng Yu and Wenyi Hong and Ji Qi and Yan Wang and Junhui Ji and Zhuoyi Yang and Lei Zhao and Xixuan Song and Jiazheng Xu and Bin Xu and Juanzi Li and Yuxiao Dong and Ming Ding and Jie Tang},
      year={2023},
      eprint={2311.03079},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}