File size: 1,005 Bytes
c20c9d2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 |
---
license: apache-2.0
---
```
import torch
import os
from transformers import AutoTokenizer, AutoModel
from icecream import ic
import time
class DocOwlInfer():
def __init__(self, ckpt_path):
self.tokenizer = AutoTokenizer.from_pretrained(ckpt_path, use_fast=False)
self.model = AutoModel.from_pretrained(ckpt_path, trust_remote_code=True, low_cpu_mem_usage=True, torch_dtype=torch.float16, device_map='auto')
self.model.init_processor(tokenizer=self.tokenizer, basic_image_size=504, crop_anchors='grid_12')
def inference(self, images, query):
messages = [{'role': 'USER', 'content': '<|image|>'*len(images)+query}]
answer = self.model.chat(messages=messages, images=images, tokenizer=self.tokenizer)
return answer
docowl = DocOwlInfer(ckpt_path='mPLUG/DocOwl2')
images = ['/nas-alinlp/anwenhu/tmp/paper.png']
query = "What is this paper about, provide detailed information."
answer = docowl.inference(images, query)
‘’‘
|