Emu2-Chat

Paper | 🤗HF Demo | Demo | Project Page | Github

Model Weights

Model name	Weight
Emu2	🤗 HF link
Emu2-Chat	🤗 HF link
Emu2-Gen	🤗 HF link

Inference (Huggingface Version)

Single GPU

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


tokenizer = AutoTokenizer.from_pretrained("BAAI/Emu2-Chat")

model = AutoModelForCausalLM.from_pretrained(
    "BAAI/Emu2-Chat",
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    trust_remote_code=True).to('cuda').eval()


# `[<IMG_PLH>]` is the image placeholder which will be replaced by image embeddings. 
# the number of `[<IMG_PLH>]` should be equal to the number of input images

query = '[<IMG_PLH>]Describe the image in details:' 
image = Image.open(requests.get('https://github.com/baaivision/Emu/Emu2/examples/blue_black_1_top_left.jpg?raw=true',stream=True).raw).convert('RGB')


inputs = model.build_input_ids(
    text=[query],
    tokenizer=tokenizer,
    image=[image]
)

with torch.no_grad():
     outputs = model.generate(
        input_ids=inputs["input_ids"],
        attention_mask=inputs["attention_mask"],
        image=inputs["image"].to(torch.bfloat16),
        max_new_tokens=64,
        length_penalty=-1)

output_text = tokenizer.batch_decode(outputs, skip_special_tokens=True)

Interleaved image and text

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


tokenizer = AutoTokenizer.from_pretrained("BAAI/Emu2-Chat")

model = AutoModelForCausalLM.from_pretrained(
    "BAAI/Emu2-Chat",
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    trust_remote_code=True).to('cuda').eval()

# `[<IMG_PLH>]` is the image placeholder which will be replaced by image embeddings. 
# the number of `[<IMG_PLH>]` should be equal to the number of input images

query = "[<IMG_PLH>][red, white, 3, bottom left].[<IMG_PLH>][yellow, white, 2, top left].[<IMG_PLH>][green, black, 4, bottom right][<IMG_PLH>]"

images = [
    Image.open(requests.get('https://github.com/baaivision/Emu/Emu2/examples/red_white_3_bottom_left.jpg?raw=true',stream=True).raw).convert('RGB'),
    Image.open(requests.get('https://github.com/baaivision/Emu/Emu2/examples/yellow_white_2_top_right.jpg?raw=true',stream=True).raw).convert('RGB'),
    Image.open(requests.get('https://github.com/baaivision/Emu/Emu2/examples/green_black_4_bottom_right.jpg?raw=true',stream=True).raw).convert('RGB'),
    Image.open(requests.get('https://github.com/baaivision/Emu/Emu2/examples/blue_black_1_top_left.jpg?raw=true',stream=True).raw).convert('RGB'),
]

inputs = model.build_input_ids(
    text=[query],
    tokenizer=tokenizer,
    image=images

)

with torch.no_grad():
     outputs = model.generate(
        input_ids=inputs["input_ids"],
        attention_mask=inputs["attention_mask"],
        image=inputs["image"].to(torch.bfloat16),
        max_new_tokens=64,
        length_penalty=-1)

output_text = tokenizer.batch_decode(outputs, skip_special_tokens=True)

Multi GPU

from PIL import Image 
import requests
import torch 
from transformers import AutoModelForCausalLM, AutoTokenizer
from accelerate import init_empty_weights, infer_auto_device_map, load_checkpoint_and_dispatch

tokenizer = AutoTokenizer.from_pretrained("BAAI/Emu2-Chat")

with init_empty_weights():
     model = AutoModelForCausalLM.from_pretrained(
        "BAAI/Emu2-Chat",
        torch_dtype=torch.bfloat16,
        low_cpu_mem_usage=True,
        trust_remote_code=True)  

device_map = infer_auto_device_map(model, max_memory={0:'38GiB',1:'38GiB',}, no_split_module_classes=['Block','LlamaDecoderLayer'])  
# input and output logits should be on same device
device_map["model.decoder.lm.lm_head"] = 0

model = load_checkpoint_and_dispatch(
    model, 
    'local/path/to/hf/version/Emu2-Chat/model',
    device_map=device_map).eval()

# `[<IMG_PLH>]` is the image placeholder which will be replaced by image embeddings. 
# the number of `[<IMG_PLH>]` should be equal to the number of input images

query = '[<IMG_PLH>]Describe the image in details:' 
image = Image.open(requests.get('https://github.com/baaivision/Emu/Emu2/examples/blue_black_1_top_left.jpg?raw=true',stream=True).raw).convert('RGB')

inputs = model.build_input_ids(
    text=[query],
    tokenizer=tokenizer,
    image=[image]

)

with torch.no_grad():
     outputs = model.generate(
        input_ids=inputs["input_ids"],
        attention_mask=inputs["attention_mask"],
        image=inputs["image"].to(torch.bfloat16),
        max_new_tokens=64,
        length_penalty=-1)

output_text = tokenizer.batch_decode(outputs, skip_special_tokens=True)

Interleaved image and text

from PIL import Image 
import requests
import torch 
from transformers import AutoModelForCausalLM, AutoTokenizer
from accelerate import init_empty_weights, infer_auto_device_map, load_checkpoint_and_dispatch

tokenizer = AutoTokenizer.from_pretrained("BAAI/Emu2-Chat")

with init_empty_weights():
     model = AutoModelForCausalLM.from_pretrained(
        "BAAI/Emu2-Chat",
        torch_dtype=torch.bfloat16,
        low_cpu_mem_usage=True,
        trust_remote_code=True)  

device_map = infer_auto_device_map(model, max_memory={0:'38GiB',1:'38GiB',}, no_split_module_classes=['Block','LlamaDecoderLayer'])  
# input and output logits should be on same device
device_map["model.decoder.lm.lm_head"] = 0

model = load_checkpoint_and_dispatch(
    model, 
    'local/path/to/hf/version/Emu2-Chat/model',
    device_map=device_map).eval()

# `[<IMG_PLH>]` is the image placeholder which will be replaced by image embeddings. 
# the number of `[<IMG_PLH>]` should be equal to the number of input images
query = "[<IMG_PLH>][red, white, 3, bottom left].[<IMG_PLH>][yellow, white, 2, top left].[<IMG_PLH>][green, black, 4, bottom right][<IMG_PLH>]"

images = [
    Image.open(requests.get('https://github.com/baaivision/Emu/Emu2/examples/red_white_3_bottom_left.jpg?raw=true',stream=True).raw).convert('RGB'),
    Image.open(requests.get('https://github.com/baaivision/Emu/Emu2/examples/yellow_white_2_top_right.jpg?raw=true',stream=True).raw).convert('RGB'),
    Image.open(requests.get('https://github.com/baaivision/Emu/Emu2/examples/green_black_4_bottom_right.jpg?raw=true',stream=True).raw).convert('RGB'),
    Image.open(requests.get('https://github.com/baaivision/Emu/Emu2/examples/blue_black_1_top_left.jpg?raw=true',stream=True).raw).convert('RGB'),
]

inputs = model.build_input_ids(
    text=[query],
    tokenizer=tokenizer,
    image=images

)

with torch.no_grad():
     outputs = model.generate(
        input_ids=inputs["input_ids"],
        attention_mask=inputs["attention_mask"],
        image=inputs["image"].to(torch.bfloat16),
        max_new_tokens=64,
        length_penalty=-1)

output_text = tokenizer.batch_decode(outputs, skip_special_tokens=True)

Quantization

Check quantization guidance at transformers

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


tokenizer = AutoTokenizer.from_pretrained("BAAI/Emu2-Chat")

model = AutoModelForCausalLM.from_pretrained(
    "BAAI/Emu2-Chat",
    load_in_4bit=True,
    trust_remote_code=True, 
    bnb_4bit_compute_dtype=torch.float16).eval()

query = '[<IMG_PLH>]Describe the image in details:' 
image = Image.open(requests.get('https://github.com/baaivision/Emu/Emu2/examples/blue_black_1_top_left.jpg?raw=true',stream=True).raw).convert('RGB')

inputs = model.build_input_ids(
    text=[query],
    tokenizer=tokenizer,
    image=[image]

)

with torch.no_grad():
     outputs = model.generate(
        input_ids=inputs["input_ids"],
        attention_mask=inputs["attention_mask"],
        image=inputs["image"].to(torch.float16), # should be torch.float16
        max_new_tokens=64,
        length_penalty=-1)

output_text = tokenizer.batch_decode(outputs, skip_special_tokens=True)

Citation

If you find Emu2 useful for your research and applications, please consider starring this repository and citing:

@article{Emu2,
    title={Generative Multimodal Models are In-Context Learners}, 
    author={Quan Sun and Yufeng Cui and Xiaosong Zhang and Fan Zhang and Qiying Yu and Zhengxiong Luo and Yueze Wang and Yongming Rao and Jingjing Liu and Tiejun Huang and Xinlong Wang},
    publisher={arXiv preprint arXiv:2312.13286},
    year={2023},
}

Downloads last month: 845

Spaces using BAAI/Emu2-Chat 3

Paper for BAAI/Emu2-Chat

Generative Multimodal Models are In-Context Learners

Paper • 2312.13286 • Published Dec 20, 2023 • 36