File size: 23,342 Bytes
a5f8592 921f508 a5f8592 921f508 a5f8592 921f508 a5f8592 921f508 a5f8592 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 |
---
license: cc-by-nc-4.0
pipeline_tag: image-text-to-text
library_name: transformers
base_model:
- google/paligemma-3b-mix-448
- Qwen/Qwen2.5-0.5B-Instruct
base_model_relation: merge
language:
- multilingual
tags:
- eagle
- VLM
---
# Eagle-2
[\[📂 GitHub\]](https://github.com/NVlabs/EAGLE) [\[📜 Eagle2 Tech Report\]](TODO)
[\[🗨️ Chat Demo\]](http://eagle-vlm.xyz/) [\[🤗 HF Demo\]](TODO)
## Introduction
We are thrilled to release our latest Eagle2 series Vision-Language Model. Open-source Vision-Language Models (VLMs) have made significant strides in narrowing the gap with proprietary models. However, critical details about data strategies and implementation are often missing, limiting reproducibility and innovation. In this project, we focus on VLM post-training from a data-centric perspective, sharing insights into building effective data strategies from scratch. By combining these strategies with robust training recipes and model design, we introduce Eagle 2, a family of performant VLMs. Our work aims to empower the open-source community to develop competitive VLMs with transparent processes.
In this repo, we are open-sourcing Eagle2-9B, which strikes the perfect balance between performance and inference speed.
## Model Zoo
We provide the following models:
| model name | LLM | Vision | Max Length| HF Link|
| ----------- | ------- |---------|-|-|
| Eagle2-1B | [Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) | Siglip | 16K| [🤗 link](https://huggingface.co/NVIDIA/Eagle2-1B)|
| Eagle2-2B | [Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) | Siglip | 16K| [🤗 link](https://huggingface.co/NVIDIA/Eagle2-2B)|
| Eagle2-9B | [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) | Siglip+ConvNext | 16K| [🤗 link](https://huggingface.co/NVIDIA/Eagle2-9B)|
| Eagle2-32B | [Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) | Siglip+ConvNext | 16K| [🤗 link](https://huggingface.co/NVIDIA/Eagle2-32B)|
## Benchmark Results
| Benchmark | LLaVa-One-Vision-0.5B | InternVL2-1B | InternVL2.5-1B |Qwen2-VL-2B| Eagle2-1B|
| :--------------------------: | :------------------: | :----------------: | :----------: |:----------: |:----------: |
| DocVQA<sub>test</sub> | 70.0 | 81.7 | 84.8 |90.1|81.8|
| ChartQA<sub>test</sub> | 61.4 | 72.9 | 75.9 |73.0|77.0|
| InfoVQA<sub>test</sub> | 41.8 | 50.9 | 56.0 |65.5|54.8|
| TextVQA<sub>val</sub> | - | 70.0 | 72.0 |79.7|76.6|
| OCRBench | 565 | 754 | 785 |809|767|
| MME<sub>sum</sub> | 1438.0 | 1794.4 | 1950.5 | 1872.0| 1790.2|
| RealWorldQA | 55.6 | 50.3 | 57.5 |62.6|55.4|
| AI2D<sub>test</sub> | 57.1 | 64.1 | 69.3 | 74.7 |70.9|
| MMMU<sub>val</sub> | 31.4 | 36.7 | 40.9 |41.1|38.8|
| MMVet<sub>GPT-4-Turbo</sub> | 32.2 | 32.7 | 48.8 | 49.5|40.9| HallBench<sub>avg</sub> | 27.9 | 34.0 | 39.0 |**41.7**|35.3
| MathVista<sub>testmini</sub> | 33.8 | 37.7 | 43.2 |43.0|45.3|
| MMstar | 37.7 | 45.7 | 50.1|48.0|48.5|
## Quick Start
We provide a [inference script](./demo.py) to help you quickly start using the model. We support different input types:
- pure text input
- single image input
- multiple image input
- video input
### 0. Install the dependencies
```bash
pip install transformers==4.37.2
pip install flash-attn
```
**Note**: Latest version of transformers if not compatible with the model.
### 1. Prepare the Model worker
<details>
<summary>Click to expand</summary>
```python
"""
A model worker executes the model.
Copied and modified from https://github.com/OpenGVLab/InternVL/blob/main/streamlit_demo/model_worker.py
"""
# Importing torch before transformers can cause `segmentation fault`
from transformers import AutoModel, AutoTokenizer, TextIteratorStreamer, AutoConfig
import argparse
import base64
import json
import os
import decord
import threading
import time
from io import BytesIO
from threading import Thread
import math
import requests
import torch
import torchvision.transforms as T
from PIL import Image
from torchvision.transforms.functional import InterpolationMode
import numpy as np
IMAGENET_MEAN = (0.485, 0.456, 0.406)
IMAGENET_STD = (0.229, 0.224, 0.225)
SIGLIP_MEAN = (0.5, 0.5, 0.5)
SIGLIP_STD = (0.5, 0.5, 0.5)
def get_seq_frames(total_num_frames, desired_num_frames=-1, stride=-1):
"""
Calculate the indices of frames to extract from a video.
Parameters:
total_num_frames (int): Total number of frames in the video.
desired_num_frames (int): Desired number of frames to extract.
Returns:
list: List of indices of frames to extract.
"""
assert desired_num_frames > 0 or stride > 0 and not (desired_num_frames > 0 and stride > 0)
if stride > 0:
return list(range(0, total_num_frames, stride))
# Calculate the size of each segment from which a frame will be extracted
seg_size = float(total_num_frames - 1) / desired_num_frames
seq = []
for i in range(desired_num_frames):
# Calculate the start and end indices of each segment
start = int(np.round(seg_size * i))
end = int(np.round(seg_size * (i + 1)))
# Append the middle index of the segment to the list
seq.append((start + end) // 2)
return seq
def build_video_prompt(meta_list, num_frames, time_position=False):
# if time_position is True, the frame_timestamp is used.
# 1. pass time_position, 2. use env TIME_POSITION
time_position = os.environ.get("TIME_POSITION", time_position)
prefix = f"This is a video:\n"
for i in range(num_frames):
if time_position:
frame_txt = f"Frame {i+1} sampled at {meta_list[i]:.2f} seconds: <image>\n"
else:
frame_txt = f"Frame {i+1}: <image>\n"
prefix += frame_txt
return prefix
def load_video(video_path, num_frames=64, frame_cache_root=None):
if isinstance(video_path, str):
video = decord.VideoReader(video_path)
elif isinstance(video_path, dict):
assert False, 'we not support vidoe: "video_path" as input'
fps = video.get_avg_fps()
sampled_frames = get_seq_frames(len(video), num_frames)
samepld_timestamps = [i / fps for i in sampled_frames]
frames = video.get_batch(sampled_frames).asnumpy()
images = [Image.fromarray(frame) for frame in frames]
return images, build_video_prompt(samepld_timestamps, len(images), time_position=True)
def load_image(image):
if isinstance(image, str) and os.path.exists(image):
return Image.open(image)
elif isinstance(image, dict):
if 'disk_path' in image:
return Image.open(image['disk_path'])
elif 'base64' in image:
return Image.open(BytesIO(base64.b64decode(image['base64'])))
elif 'url' in image:
response = requests.get(image['url'])
return Image.open(BytesIO(response.content))
elif 'bytes' in image:
return Image.open(BytesIO(image['bytes']))
else:
raise ValueError(f'Invalid image: {image}')
else:
raise ValueError(f'Invalid image: {image}')
def build_transform(input_size, norm_type='imagenet'):
if norm_type == 'imagenet':
MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
elif norm_type == 'siglip':
MEAN, STD = SIGLIP_MEAN, SIGLIP_STD
transform = T.Compose([
T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
T.ToTensor(),
T.Normalize(mean=MEAN, std=STD)
])
return transform
def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
"""
previous version mainly foucs on ratio.
We also consider area ratio here.
"""
best_factor = float('-inf')
best_ratio = (1, 1)
area = width * height
for ratio in target_ratios:
target_aspect_ratio = ratio[0] / ratio[1]
ratio_diff = abs(aspect_ratio - target_aspect_ratio)
area_ratio = (ratio[0]*ratio[1]*image_size*image_size)/ area
"""
new area > 60% of original image area is enough.
"""
factor_based_on_area_n_ratio = min((ratio[0]*ratio[1]*image_size*image_size)/ area, 0.6)* \
min(target_aspect_ratio/aspect_ratio, aspect_ratio/target_aspect_ratio)
if factor_based_on_area_n_ratio > best_factor:
best_factor = factor_based_on_area_n_ratio
best_ratio = ratio
return best_ratio
def dynamic_preprocess(image, min_num=1, max_num=6, image_size=448, use_thumbnail=False):
orig_width, orig_height = image.size
aspect_ratio = orig_width / orig_height
# calculate the existing image aspect ratio
target_ratios = set(
(i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if
i * j <= max_num and i * j >= min_num)
target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])
# find the closest aspect ratio to the target
target_aspect_ratio = find_closest_aspect_ratio(
aspect_ratio, target_ratios, orig_width, orig_height, image_size)
# calculate the target width and height
target_width = image_size * target_aspect_ratio[0]
target_height = image_size * target_aspect_ratio[1]
blocks = target_aspect_ratio[0] * target_aspect_ratio[1]
# resize the image
resized_img = image.resize((target_width, target_height))
processed_images = []
for i in range(blocks):
box = (
(i % (target_width // image_size)) * image_size,
(i // (target_width // image_size)) * image_size,
((i % (target_width // image_size)) + 1) * image_size,
((i // (target_width // image_size)) + 1) * image_size
)
# split the image
split_img = resized_img.crop(box)
processed_images.append(split_img)
assert len(processed_images) == blocks
if use_thumbnail and len(processed_images) != 1:
thumbnail_img = image.resize((image_size, image_size))
processed_images.append(thumbnail_img)
return processed_images
def split_model(model_path, device):
device_map = {}
world_size = torch.cuda.device_count()
config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
num_layers = config.llm_config.num_hidden_layers
print('world_size', world_size)
num_layers_per_gpu_ = math.floor(num_layers / (world_size - 1))
num_layers_per_gpu = [num_layers_per_gpu_] * world_size
num_layers_per_gpu[device] = num_layers - num_layers_per_gpu_ * (world_size-1)
print(num_layers_per_gpu)
layer_cnt = 0
for i, num_layer in enumerate(num_layers_per_gpu):
for j in range(num_layer):
device_map[f'language_model.model.layers.{layer_cnt}'] = i
layer_cnt += 1
device_map['vision_model'] = device
device_map['mlp1'] = device
device_map['language_model.model.tok_embeddings'] = device
device_map['language_model.model.embed_tokens'] = device
device_map['language_model.output'] = device
device_map['language_model.model.norm'] = device
device_map['language_model.lm_head'] = device
device_map['language_model.model.rotary_emb'] = device
device_map[f'language_model.model.layers.{num_layers - 1}'] = device
return device_map
class ModelWorker:
def __init__(self, model_path, model_name,
load_8bit, device):
if model_path.endswith('/'):
model_path = model_path[:-1]
if model_name is None:
model_paths = model_path.split('/')
if model_paths[-1].startswith('checkpoint-'):
self.model_name = model_paths[-2] + '_' + model_paths[-1]
else:
self.model_name = model_paths[-1]
else:
self.model_name = model_name
print(f'Loading the model {self.model_name}')
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True, use_fast=False)
tokens_to_keep = ['<box>', '</box>', '<ref>', '</ref>']
tokenizer.additional_special_tokens = [item for item in tokenizer.additional_special_tokens if item not in tokens_to_keep]
self.tokenizer = tokenizer
config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
model_type = config.vision_config.model_type
self.device = torch.cuda.current_device()
if model_type == 'siglip_vision_model':
self.norm_type = 'siglip'
elif model_type == 'MOB':
self.norm_type = 'siglip'
else:
self.norm_type = 'imagenet'
if any(x in model_path.lower() for x in ['34b']):
device_map = split_model(model_path, self.device)
else:
device_map = None
if device_map is not None:
self.model = AutoModel.from_pretrained(model_path, torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
device_map=device_map,
trust_remote_code=True,
load_in_8bit=load_8bit).eval()
else:
self.model = AutoModel.from_pretrained(model_path, torch_dtype=torch.bfloat16,
trust_remote_code=True,
load_in_8bit=load_8bit).eval()
if not load_8bit and device_map is None:
self.model = self.model.to(device)
self.load_8bit = load_8bit
self.model_path = model_path
self.image_size = self.model.config.force_image_size
self.context_len = tokenizer.model_max_length
self.per_tile_len = 256
def reload_model(self):
del self.model
torch.cuda.empty_cache()
if self.device == 'auto':
os.environ['CUDA_LAUNCH_BLOCKING'] = '1'
# This can make distributed deployment work properly
self.model = AutoModel.from_pretrained(
self.model_path,
load_in_8bit=self.load_8bit,
torch_dtype=torch.bfloat16,
device_map=self.device_map,
trust_remote_code=True).eval()
else:
self.model = AutoModel.from_pretrained(
self.model_path,
load_in_8bit=self.load_8bit,
torch_dtype=torch.bfloat16,
trust_remote_code=True).eval()
if not self.load_8bit and not self.device == 'auto':
self.model = self.model.cuda()
@torch.inference_mode()
def generate(self, params):
system_message = params['prompt'][0]['content']
send_messages = params['prompt'][1:]
max_input_tiles = params['max_input_tiles']
temperature = params['temperature']
top_p = params['top_p']
max_new_tokens = params['max_new_tokens']
repetition_penalty = params['repetition_penalty']
video_frame_num = params.get('video_frame_num', 64)
do_sample = True if temperature > 0.0 else False
global_image_cnt = 0
history, pil_images, max_input_tile_list = [], [], []
for message in send_messages:
if message['role'] == 'user':
prefix = ''
if 'image' in message:
for image_data in message['image']:
pil_images.append(load_image(image_data))
prefix = prefix + f'<image {global_image_cnt + 1}><image>\n'
global_image_cnt += 1
max_input_tile_list.append(max_input_tiles)
if 'video' in message:
for video_data in message['video']:
video_frames, tmp_prefix = load_video(video_data, num_frames=video_frame_num)
pil_images.extend(video_frames)
prefix = prefix + tmp_prefix
global_image_cnt += len(video_frames)
max_input_tile_list.extend([1] * len(video_frames))
content = prefix + message['content']
history.append([content, ])
else:
history[-1].append(message['content'])
question, history = history[-1][0], history[:-1]
if global_image_cnt == 1:
question = question.replace('<image 1><image>\n', '<image>\n')
history = [[item[0].replace('<image 1><image>\n', '<image>\n'), item[1]] for item in history]
try:
assert len(max_input_tile_list) == len(pil_images), 'The number of max_input_tile_list and pil_images should be the same.'
except Exception as e:
from IPython import embed; embed()
exit()
print(f'Error: {e}')
print(f'max_input_tile_list: {max_input_tile_list}, pil_images: {pil_images}')
# raise e
old_system_message = self.model.system_message
self.model.system_message = system_message
transform = build_transform(input_size=self.image_size, norm_type=self.norm_type)
if len(pil_images) > 0:
max_input_tiles_limited_by_contect = params['max_input_tiles']
while True:
image_tiles = []
for current_max_input_tiles, pil_image in zip(max_input_tile_list, pil_images):
if self.model.config.dynamic_image_size:
tiles = dynamic_preprocess(
pil_image, image_size=self.image_size, max_num=min(current_max_input_tiles, max_input_tiles_limited_by_contect),
use_thumbnail=self.model.config.use_thumbnail)
else:
tiles = [pil_image]
image_tiles += tiles
if (len(image_tiles) * self.per_tile_len < self.context_len):
break
else:
max_input_tiles_limited_by_contect -= 2
if max_input_tiles_limited_by_contect < 1:
break
pixel_values = [transform(item) for item in image_tiles]
pixel_values = torch.stack(pixel_values).to(self.model.device, dtype=torch.bfloat16)
print(f'Split images to {pixel_values.shape}')
else:
pixel_values = None
generation_config = dict(
num_beams=1,
max_new_tokens=max_new_tokens,
do_sample=do_sample,
temperature=temperature,
repetition_penalty=repetition_penalty,
max_length=self.context_len,
top_p=top_p,
)
response = self.model.chat(
tokenizer=self.tokenizer,
pixel_values=pixel_values,
question=question,
history=history,
return_history=False,
generation_config=generation_config,
)
self.model.system_message = old_system_message
return {'text': response, 'error_code': 0}
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--model-path', type=str, default='NVIDIA/Eagle-2-1B')
parser.add_argument('--model-name', type=str, default='Eagle-2-1B')
parser.add_argument('--device', type=str, default='cuda')
parser.add_argument('--load-8bit', action='store_true')
args = parser.parse_args()
print(f'args: {args}')
worker = ModelWorker(
args.model_path,
args.model_name,
args.load_8bit,
args.device)
```
</details>
### 2. Prepare the Prompt
- Single image input
```python
prompt = [
{'role': 'system', 'content': 'You are a helpful assistant.'},
{'role': 'user', 'content': 'Describe this image in details.',
'image':[
{'url': 'https://www.nvidia.com/content/dam/en-zz/Solutions/about-nvidia/logo-and-brand/[email protected]'}
],
}
]
```
- Multiple image input
```python
prompt = [
{'role': 'system', 'content': 'You are a helpful assistant.'},
{'role': 'user', 'content': 'Describe these two images in details.',
'image':[
{'url': 'https://www.nvidia.com/content/dam/en-zz/Solutions/about-nvidia/logo-and-brand/[email protected]'},
{'url': 'https://www.nvidia.com/content/dam/en-zz/Solutions/about-nvidia/logo-and-brand/[email protected]'}
],
}
]
```
- Video input
```python
prompt = [
{'role': 'system', 'content': 'You are a helpful assistant.'},
{'role': 'user', 'content': 'Describe this video in details.',
'video':[
'path/to/your/video.mp4'
],
}
]
```
### 3. Generate the response
```python
params = {
'prompt': prompt,
'max_input_tiles': 24,
'temperature': 0.7,
'top_p': 1.0,
'max_new_tokens': 4096,
'repetition_penalty': 1.0,
}
worker.generate(params)
```
## TODO
- [ ] Support vLLM Inference
- [ ] Provide AWQ Quantization Weights
- [ ] Provide fine-tuning scripts
## License/Terms of Use
- The code is released under the Apache 2.0 license as found in the [LICENSE](https://huggingface.co/NVEagle/Eagle-X5-13B-Chat/blob/main/LICENSE) file.
- The pretrained model weights are released under the [Creative Commons Attribution: Non-Commercial 4.0 International](https://spdx.org/licenses/CC-BY-NC-4.0) <br>
- The service is a research preview intended for non-commercial use only, and is subject to the following licenses and terms:
- Model License of Qwen2.5-7B-Instruct: [Apache-2.0](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct/blob/main/LICENSE)
- Model License of PaliGemma: [Gemma license](https://ai.google.dev/gemma/terms)
## Citation
## Ethical Considerations
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
|