Spaces:
BAAI
/
Running on L40S

File size: 1,563 Bytes
261b6ba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
# -*- coding: utf-8 -*-
from PIL import Image
from transformers import AutoTokenizer, AutoModel, AutoImageProcessor, AutoModelForCausalLM
from transformers.generation.configuration_utils import GenerationConfig
import torch

from emu3.mllm.processing_emu3 import Emu3Processor


# model path
EMU_HUB = "BAAI/Emu3-Chat"
VQ_HUB = "BAAI/Emu3-VisionTokenizer"

# prepare model and processor
model = AutoModelForCausalLM.from_pretrained(
    EMU_HUB,
    device_map="cuda:0",
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(EMU_HUB, trust_remote_code=True)
image_processor = AutoImageProcessor.from_pretrained(VQ_HUB, trust_remote_code=True)
image_tokenizer = AutoModel.from_pretrained(VQ_HUB, device_map="cuda:0", trust_remote_code=True).eval()
processor = Emu3Processor(image_processor, image_tokenizer, tokenizer)

# prepare input
text = "Please describe the image"
image = Image.open("assets/demo.png")

inputs = processor(
    text=text,
    image=image,
    mode='U',
    padding_side="left",
    padding="longest",
    return_tensors="pt",
)

# prepare hyper parameters
GENERATION_CONFIG = GenerationConfig(pad_token_id=tokenizer.pad_token_id, bos_token_id=tokenizer.bos_token_id, eos_token_id=tokenizer.eos_token_id)

# generate
outputs = model.generate(
    inputs.input_ids.to("cuda:0"),
    GENERATION_CONFIG,
    max_new_tokens=320,
)

outputs = outputs[:, inputs.input_ids.shape[-1]:]
print(processor.batch_decode(outputs, skip_special_tokens=True)[0])