File size: 8,444 Bytes
d5d3d11 |
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 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 |
---
language:
- en
---
[🤗 HF Demo](https://huggingface.co/spaces/BAAI/Emu2) | [Demo](https://emu.ssi.plus) | [Project Page](https://baaivision.github.io/emu2/)
## Model Weights
| Model name | Weight |
| ------------------ | ------------------------------------------------------- |
| **Emu2** | [🤗 HF link](https://huggingface.co/BAAI/Emu2) |
| **Emu2-Chat** | [🤗 HF link](https://huggingface.co/BAAI/Emu2-Chat) |
| **Emu2-Gen** | [🤗 HF link](https://huggingface.co/BAAI/Emu2-Gen) |
## Inference (Huggingface Version)
#### Single GPU
```python
from PIL import Image
import requests
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("BAAI/Emu2")
model = AutoModelForCausalLM.from_pretrained(
"BAAI/Emu2",
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
```python
from PIL import Image
import requests
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("BAAI/Emu2")
model = AutoModelForCausalLM.from_pretrained(
"BAAI/Emu2",
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
```python
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")
with init_empty_weights():
model = AutoModelForCausalLM.from_pretrained(
"BAAI/Emu2",
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/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
```python
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")
with init_empty_weights():
model = AutoModelForCausalLM.from_pretrained(
"BAAI/Emu2",
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/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](https://huggingface.co/docs/transformers/v4.28.0/main_classes/quantization)
```python
from PIL import Image
import requests
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("BAAI/Emu2")
model = AutoModelForCausalLM.from_pretrained(
"BAAI/Emu2",
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)
``` |